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. 23-RESID-POST-AA
    6. 131057
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ند
    -0.07
    蛇
    -0.07
    ديمق
    -0.07
    ichier
    -0.06
     Fr
    -0.06
    ioxide
    -0.06
    ereal
    -0.06
    .getResources
    -0.06
    awks
    -0.06
    ustria
    -0.06
    POSITIVE LOGITS
    において
    0.07
     having
    0.07
     attacking
    0.07
     kiếm
    0.07
    审理
    0.07
    買い物
    0.07
     vazgeç
    0.07
     rais
    0.07
     gusto
    0.07
    .menuStrip
    0.07
    Activations Density 0.020%

    No Known Activations