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. 59511
    Prev
    Next
    INDEX
    Explanations

    kwargs

    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
    开门
    -0.08
     sunrise
    -0.08
    hma
    -0.07
    rei
    -0.07
     prevalent
    -0.07
     frustrations
    -0.07
    _ARM
    -0.07
     commitments
    -0.07
    支柱
    -0.07
    发展中
    -0.07
    POSITIVE LOGITS
    ']?>
    0.08
    ปลอด
    0.07
    可愛
    0.07
     cant
    0.07
     kwargs
    0.07
     категор
    0.06
     �
    0.06
    .Cursor
    0.06
     Knight
    0.06
    уг
    0.06
    Activations Density 0.001%

    No Known Activations