© 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. 11-RESID-POST-AA
    11. 56976
    Prev
    Next
    INDEX
    Explanations

    importance

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    挺
    -0.07
    *******/↵
    -0.07
    ธนา
    -0.07
     sluggish
    -0.07
    ivery
    -0.07
     giới
    -0.07
     thiếu
    -0.07
    或者其他
    -0.06
    tty
    -0.06
    .TAG
    -0.06
    POSITIVE LOGITS
     importance
    0.08
     thoughts
    0.07
     trabalho
    0.07
    .email
    0.07
    ;;;;;;;;;;;;;;;;
    0.07
    instead
    0.06
    Space
    0.06
    itespace
    0.06
    Ingredient
    0.06
    documents
    0.06
    Activations Density 0.017%

    No Known Activations