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. 131018
    Prev
    Next
    INDEX
    Explanations

    Non-English 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
    民主党
    -0.08
     brilliant
    -0.07
     BitmapFactory
    -0.07
     Drama
    -0.07
    商业地产
    -0.07
    谲
    -0.07
     Organic
    -0.07
     MOT
    -0.06
    总工会
    -0.06
    สมาคม
    -0.06
    POSITIVE LOGITS
    せて
    0.08
     lo
    0.08
    :text
    0.07
    הוד
    0.07
    集群
    0.07
     בזכ
    0.07
    🔤
    0.07
     pope
    0.07
    שות
    0.07
     hl
    0.07
    Activations Density 0.095%

    No Known Activations