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. 24579
    Prev
    Next
    INDEX
    Explanations

    migrating

    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
    tbody
    -0.07
    .listView
    -0.07
    摆在
    -0.07
    boxed
    -0.06
    严格落实
    -0.06
    checkBox
    -0.06
    Reload
    -0.06
     ваши
    -0.06
    下去
    -0.06
    from
    -0.06
    POSITIVE LOGITS
    젝
    0.08
    揸
    0.07
     quart
    0.07
     detection
    0.07
    ョ
    0.07
     theoretical
    0.07
     computed
    0.07
    험
    0.07
    不在乎
    0.07
    criptor
    0.06
    Activations Density 0.043%

    No Known Activations