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. 131062
    Prev
    Next
    INDEX
    Explanations

    increase

    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
     yalnız
    -0.07
     nadzieję
    -0.07
    .getSimpleName
    -0.07
    祆
    -0.06
    PELL
    -0.06
    接地气
    -0.06
    轵
    -0.06
    📍
    -0.06
    家居
    -0.06
    工业大学
    -0.06
    POSITIVE LOGITS
     ctr
    0.08
     FormBuilder
    0.07
    CTRL
    0.07
    _row
    0.07
    akte
    0.07
    何况
    0.07
     eyed
    0.07
     rr
    0.07
    orsi
    0.07
     MD
    0.07
    Activations Density 0.085%

    No Known Activations