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. 19-RESID-POST-AA
    6. 24661
    Prev
    Next
    INDEX
    Explanations

    validating results/models

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المنتدى
    -0.07
    征求意见
    -0.07
    مستشفى
    -0.07
     indonesia
    -0.07
    أحدث
    -0.07
     בשב
    -0.07
    丰富多彩
    -0.07
     systematic
    -0.07
     댓글
    -0.06
    腼
    -0.06
    POSITIVE LOGITS
     cruising
    0.07
    ähl
    0.07
    נדר
    0.07
    وجه
    0.07
    acağını
    0.06
     NOM
    0.06
     Barr
    0.06
    かかり
    0.06
    憬
    0.06
    ectl
    0.06
    Activations Density 0.090%

    No Known Activations