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. 131013
    Prev
    Next
    INDEX
    Explanations

    Formal language

    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
     thumbnail
    -0.07
     overl
    -0.06
    -resistant
    -0.06
     SUS
    -0.06
     �
    -0.06
     pregnancy
    -0.06
    lsa
    -0.06
    _play
    -0.06
    lastic
    -0.06
     Bethlehem
    -0.06
    POSITIVE LOGITS
     Org
    0.07
    _Var
    0.07
    _relationship
    0.07
    (section
    0.06
    믑
    0.06
     Malcolm
    0.06
    市场的
    0.06
     será
    0.06
     ofrec
    0.06
     gratuite
    0.06
    Activations Density 0.092%

    No Known Activations