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. 59375
    Prev
    Next
    INDEX
    Explanations

    Remember

    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
     sını
    -0.07
    좡
    -0.07
    泽连
    -0.07
    岢
    -0.07
     amore
    -0.07
     hà
    -0.07
    枣
    -0.06
    .Views
    -0.06
    に対して
    -0.06
    쪽
    -0.06
    POSITIVE LOGITS
     flutter
    0.08
     Remember
    0.08
    umbling
    0.07
    mapping
    0.07
    名家
    0.07
    discount
    0.07
    _VERBOSE
    0.07
     predicted
    0.07
    arranty
    0.07
    Hum
    0.07
    Activations Density 0.009%

    No Known Activations