© 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. 71837
    Prev
    Next
    INDEX
    Explanations

    fork

    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
    Not in Any Lists

    No Comments

    Negative Logits
    星座
    -0.07
     تكون
    -0.06
    bler
    -0.06
    _SPE
    -0.06
     يكون
    -0.06
    𝑘
    -0.06
     במיוחד
    -0.06
    פרק
    -0.06
    쎈
    -0.06
    juven
    -0.06
    POSITIVE LOGITS
     royalties
    0.07
    wash
    0.07
    RAM
    0.07
    ازي
    0.07
     May
    0.07
    uar
    0.07
     prox
    0.07
     rooms
    0.06
     UserId
    0.06
     RAID
    0.06
    Activations Density 0.050%

    No Known Activations