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. 130990
    Prev
    Next
    INDEX
    Explanations

    file paths

    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
     qw
    -0.08
     signals
    -0.07
    昆虫
    -0.07
    帚
    -0.07
     sortie
    -0.07
    д
    -0.07
     securities
    -0.07
    (j
    -0.07
     sâu
    -0.07
    敌人
    -0.06
    POSITIVE LOGITS
    .VERSION
    0.06
    สะดวก
    0.06
    bob
    0.06
    我想
    0.06
    谋划
    0.06
    ᨯ
    0.06
    镚
    0.06
    뭐
    0.06
    .formData
    0.06
    ้อย
    0.06
    Activations Density 0.000%

    No Known Activations