Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 88186
    Prev
    Next
    INDEX
    Explanations

    say "* or //"

    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
    Nombre
    -0.07
     Forgotten
    -0.07
     Notícias
    -0.07
    つけ
    -0.07
    .ibm
    -0.07
    ouch
    -0.07
    mouseover
    -0.06
    첨
    -0.06
    ierrez
    -0.06
    ┻
    -0.06
    POSITIVE LOGITS
     mental
    0.07
     sớ
    0.07
     department
    0.07
     SN
    0.06
     material
    0.06
    са
    0.06
     piled
    0.06
    Xã
    0.06
    ★
    0.06
    [String
    0.06
    Activations Density 0.002%

    No Known Activations