© 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. 20-TRANSCODER-HP
    7. 141975
    Prev
    Next
    INDEX
    Explanations

    solder/fluor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èķī
    -0.28
    oplay
    -0.28
    iÅŁ
    -0.28
    Dia
    -0.27
    ckt
    -0.26
    elson
    -0.24
    -être
    -0.24
    诱人
    -0.23
    ä¸įæĸŃæī©å¤§
    -0.23
     BOTH
    -0.23
    POSITIVE LOGITS
    ims
    0.30
    ies
    0.28
     beads
    0.26
     demon
    0.26
    ->
    0.26
    unos
    0.25
    typeid
    0.23
     ->
    0.23
     bead
    0.23
    æ·±æ¸Ĭ
    0.23
    Activations Density 4.722%

    No Known Activations