© 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. 15-RESID-POST-AA
    11. 81305
    Prev
    Next
    INDEX
    Explanations

    virus

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Hamm
    -0.08
    _Meta
    -0.07
    zig
    -0.07
     Planned
    -0.07
     vy
    -0.07
    +w
    -0.06
    Mini
    -0.06
     Madd
    -0.06
     finde
    -0.06
    MK
    -0.06
    POSITIVE LOGITS
    เกาหล
    0.08
     irritating
    0.07
     omdat
    0.07
    ຮ
    0.07
    שמ
    0.07
    variably
    0.07
     debacle
    0.07
     잘못
    0.07
     reinforce
    0.07
     תע
    0.07
    Activations Density 0.003%

    No Known Activations