© 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. 30246
    Prev
    Next
    INDEX
    Explanations

    play

    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
    çİ©ç¬ij
    -0.28
    ovement
    -0.26
    agal
    -0.26
    Regional
    -0.25
    .gb
    -0.25
    ä¸ĢéĹª
    -0.25
     channel
    -0.25
    derived
    -0.25
     curs
    -0.24
    riel
    -0.24
    POSITIVE LOGITS
    èģĮ称
    0.27
    lü
    0.26
    ä¸Ģ头
    0.26
     Said
    0.26
    _gem
    0.25
     suic
    0.25
    è·Łè¸ª
    0.24
    Career
    0.24
     Budd
    0.24
    entin
    0.24
    Activations Density 1.029%

    No Known Activations