© 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. 30123
    Prev
    Next
    INDEX
    Explanations

    code

    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
    Not in Any Lists

    No Comments

    Negative Logits
     presidency
    -0.28
    batis
    -0.27
    PELL
    -0.27
    é¡¿
    -0.26
    ares
    -0.26
     dominance
    -0.26
    lope
    -0.25
    ë¹Ī
    -0.25
    éĥ¨éķ¿
    -0.25
    kin
    -0.24
    POSITIVE LOGITS
     blank
    0.27
    Blank
    0.26
     Blank
    0.26
    uyá»ĥn
    0.26
     tidal
    0.25
    Instructions
    0.25
    _OPTIONS
    0.25
    .UTC
    0.24
    .Spring
    0.24
    éĤª
    0.24
    Activations Density 1.011%

    No Known Activations