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. 131059
    Prev
    Next
    INDEX
    Explanations

    can/could

    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
     Triangle
    -0.07
    =open
    -0.06
    徕
    -0.06
     CONST
    -0.06
    していた
    -0.06
    沉浸在
    -0.06
    โรงงาน
    -0.06
    ︕
    -0.06
    _mappings
    -0.06
     SUP
    -0.06
    POSITIVE LOGITS
    ┴
    0.07
    piration
    0.07
    吻
    0.07
    营养
    0.07
    (begin
    0.07
    似
    0.07
    uggestion
    0.07
    erv
    0.07
     التاريخ
    0.07
    qry
    0.07
    Activations Density 0.022%

    No Known Activations