© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 60004
    Prev
    Next
    INDEX
    Explanations

    Plurals/words ending in 's'

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    有限
    -0.07
    ѳ
    -0.07
    裴
    -0.07
    מיטב
    -0.07
    vehicle
    -0.07
    🍥
    -0.07
    忻
    -0.07
    漫长的
    -0.07
    🍊
    -0.07
     Lovely
    -0.06
    POSITIVE LOGITS
    agog
    0.08
     EV
    0.07
     })
    0.07
    袜
    0.07
    戏剧
    0.07
    녔
    0.07
     Markets
    0.07
     FIX
    0.07
     digest
    0.06
    垡
    0.06
    Activations Density 0.054%

    No Known Activations