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. 27-RESID-POST-AA
    6. 131048
    Prev
    Next
    INDEX
    Explanations

    sch

    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_27/trainer_1
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     respondsToSelector
    -0.07
    ),$
    -0.07
    ǟ
    -0.07
     /^[
    -0.07
     ObservableCollection
    -0.06
    _create
    -0.06
    🏪
    -0.06
     ****************************************************************
    -0.06
    🧿
    -0.06
    еля
    -0.06
    POSITIVE LOGITS
    _marker
    0.07
    新
    0.07
     weighting
    0.07
     soaring
    0.07
    _ms
    0.07
    romise
    0.07
     mocks
    0.07
    بة
    0.06
    הגנה
    0.06
    _group
    0.06
    Activations Density 0.000%

    No Known Activations