© 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. 18-TRANSCODER-HP
    7. 89291
    Prev
    Next
    INDEX
    Explanations

    tables and graphs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fdb
    -0.27
    $__
    -0.24
    ẩu
    -0.24
     sino
    -0.23
    seealso
    -0.23
    ticks
    -0.23
    usty
    -0.23
    eeper
    -0.23
    ixin
    -0.23
    older
    -0.23
    POSITIVE LOGITS
    åĪ¸
    0.26
    æĺ¯æľĢ好çļĦ
    0.26
     dimensions
    0.25
    ç¿Ķ
    0.25
    æĹ©æĻ¨
    0.25
    leader
    0.24
     stake
    0.24
     Dimensions
    0.24
    è´¨åľ°
    0.24
    _DESCRIPTOR
    0.24
    Activations Density 2.900%

    No Known Activations