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. 131024
    Prev
    Next
    INDEX
    Explanations

    Code testing

    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
    申請
    -0.07
    治理体系
    -0.07
    梣
    -0.07
    ธร
    -0.07
    ฟา
    -0.06
    澈
    -0.06
    ᵒ
    -0.06
     Agile
    -0.06
    doll
    -0.06
    ABCDEFGHI
    -0.06
    POSITIVE LOGITS
    ях
    0.08
    部
    0.07
     Lottery
    0.07
    ñ
    0.07
     vì
    0.07
    路
    0.07
    Ticket
    0.07
     החל
    0.07
    Extension
    0.06
    (region
    0.06
    Activations Density 0.034%

    No Known Activations