© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 69151
    Prev
    Next
    INDEX
    Explanations

    Scientific/technical language

    np_max-act-logits · gemini-2.0-flash

    dense biomedical pharmacology descriptions of mechanisms of action—receptor/enzyme interactions, signaling pathways, and modulatory relations such as agonism, antagonism, and inhibition

    oai_token-act-pair · gpt-5Triggered by @jdhshshs138
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    إنش
    -0.07
     kita
    -0.07
     jail
    -0.07
    草
    -0.06
    虫
    -0.06
    dıkl
    -0.06
     מהמ
    -0.06
     chó
    -0.06
    䴔
    -0.06
    تسم
    -0.06
    POSITIVE LOGITS
    ount
    0.07
     dav
    0.07
    Output
    0.07
    担任
    0.07
    ʂ
    0.07
    _FLAG
    0.07
    lect
    0.07
     coaches
    0.07
     Shared
    0.07
    热线
    0.07
    Activations Density 0.022%

    No Known Activations