© 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. 109393
    Prev
    Next
    INDEX
    Explanations

    you

    np_max-act-logits · gemini-2.0-flash
    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
     Alec
    -0.07
    _Ass
    -0.07
    blocked
    -0.07
     wirk
    -0.07
    veget
    -0.07
    obel
    -0.06
    (dm
    -0.06
     Prec
    -0.06
    倏
    -0.06
    腴
    -0.06
    POSITIVE LOGITS
    剽
    0.07
     שינויים
    0.07
    Japanese
    0.07
    ")){↵
    0.06
    UPI
    0.06
    不同的
    0.06
    主体责任
    0.06
    赛车
    0.06
    ($__
    0.06
    女性
    0.06
    Activations Density 0.009%

    No Known Activations