© 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. Qwen3-4B
    5. 9-TRANSCODER-HP
    7. 30393
    Prev
    Next
    INDEX
    Explanations

    world

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     zakÅĤad
    -0.35
    idd
    -0.29
    æĸ°å¸¸æĢģ
    -0.26
    çĥĿ
    -0.25
    istry
    -0.25
    æĭīå¼Ģ
    -0.25
    èĶ¸
    -0.24
    ister
    -0.24
    å°ıé¢Ŀ贷款
    -0.24
    ulis
    -0.24
    POSITIVE LOGITS
    -fi
    0.27
    SYM
    0.27
    ||
    0.25
    |=
    0.24
    (sym
    0.24
     backwards
    0.24
    ç§ijæĬĢè¿ĽæŃ¥
    0.24
    骷
    0.24
     mexico
    0.24
    agraph
    0.23
    Activations Density 0.134%

    No Known Activations