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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 5759
    Prev
    Next
    INDEX
    Explanations

    obese patients

    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
     Unfortunately
    -0.07
    溃疡
    -0.07
    ordial
    -0.07
     corr
    -0.07
     Thanks
    -0.07
    引爆
    -0.06
     forgot
    -0.06
    交融
    -0.06
    -Bold
    -0.06
     Clearly
    -0.06
    POSITIVE LOGITS
    andom
    0.07
    -js
    0.07
    mus
    0.06
    _basis
    0.06
     LONG
    0.06
     Tele
    0.06
     paul
    0.06
    úc
    0.06
    姣
    0.06
    _des
    0.06
    Activations Density 0.043%

    No Known Activations