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. 131057
    Prev
    Next
    INDEX
    Explanations

    able

    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
    ensem
    -0.08
    שום
    -0.07
    EXPECT
    -0.07
    制定了
    -0.07
    全国各地
    -0.07
     Executors
    -0.07
    사이
    -0.07
    อาจจะ
    -0.07
    (Grid
    -0.07
     whit
    -0.06
    POSITIVE LOGITS
     dismissed
    0.08
    身边
    0.07
    倒霉
    0.07
     isValid
    0.07
     predis
    0.07
     DETAILS
    0.07
    行政审批
    0.07
    救命
    0.07
    vec
    0.07
     renovation
    0.06
    Activations Density 0.000%

    No Known Activations