© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6995
    Prev
    Next
    INDEX
    Explanations

    Field

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çļĦ人æĿ¥è¯´
    -0.28
    åĪ»
    -0.27
    æľ¨è´¨
    -0.25
    .locale
    -0.24
    agg
    -0.24
    çļĦåŁİå¸Ĥ
    -0.24
    便
    -0.24
    aggio
    -0.24
    æĭľ
    -0.24
    æĸ¹éĿ¢
    -0.23
    POSITIVE LOGITS
    oph
    0.31
    shiv
    0.28
    ingly
    0.26
     hovered
    0.25
    lights
    0.25
    =search
    0.25
    ForKey
    0.25
    ters
    0.24
     [+
    0.24
    -of
    0.24
    Activations Density 0.033%

    No Known Activations