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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 71759
    Prev
    Next
    INDEX
    Explanations

    bacteria

    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
     very
    -0.08
    ซอ
    -0.07
     ora
    -0.07
     mö
    -0.07
     strSQL
    -0.07
     ise
    -0.06
     MED
    -0.06
     Nim
    -0.06
     записи
    -0.06
    绢
    -0.06
    POSITIVE LOGITS
     באותו
    0.07
    _stamp
    0.07
    价格
    0.07
    .Quad
    0.07
    充沛
    0.07
     unforgettable
    0.07
    넢
    0.07
    庱
    0.07
    -functional
    0.07
     customerId
    0.07
    Activations Density 0.004%

    No Known Activations