© 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. 40109
    Prev
    Next
    INDEX
    Explanations

    article

    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
    ingly
    -0.31
    лин
    -0.26
    LIN
    -0.25
    åŀĭ
    -0.25
     Association
    -0.25
    oit
    -0.24
    <!--[
    -0.24
    emens
    -0.24
     CPS
    -0.24
    asso
    -0.24
    POSITIVE LOGITS
    åŃ£åIJİ
    0.29
    æĢĢæĬ±
    0.28
    imas
    0.26
     éc
    0.26
    furt
    0.26
    çek
    0.26
    è¿İ
    0.25
    ża
    0.24
    egas
    0.24
    ibr
    0.24
    Activations Density 1.080%

    No Known Activations