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. 36281
    Prev
    Next
    INDEX
    Explanations

    lm

    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
    酏
    -0.08
     sympathy
    -0.07
    urniture
    -0.07
     welded
    -0.07
    鼽
    -0.07
     polygon
    -0.07
     Phần
    -0.07
     colossal
    -0.07
    獒
    -0.07
     Graphics
    -0.07
    POSITIVE LOGITS
     Hem
    0.08
     survivors
    0.07
    ney
    0.07
    _he
    0.07
    .mem
    0.06
    ﱏ
    0.06
    ham
    0.06
     Kate
    0.06
     erle
    0.06
    _ERRORS
    0.06
    Activations Density 0.006%

    No Known Activations