© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 14-TRANSCODER-HP
    7. 40932
    Prev
    Next
    INDEX
    Explanations

    os

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sliced
    -0.28
    .quick
    -0.25
    æ½ĩ
    -0.25
    ->__
    -0.25
     afterward
    -0.25
    igmatic
    -0.25
    resident
    -0.24
    裸
    -0.24
     Wr
    -0.24
    idental
    -0.23
    POSITIVE LOGITS
    iens
    0.29
    iers
    0.28
    amen
    0.27
    obi
    0.26
    åĽ¢è´Ń
    0.26
    /UI
    0.25
    boys
    0.24
    oves
    0.24
    OWN
    0.23
    .getById
    0.23
    Activations Density 0.075%

    No Known Activations