© 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. 107235
    Prev
    Next
    INDEX
    Explanations

    American

    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
    Market
    -0.27
     Market
    -0.27
     Catch
    -0.26
     Clim
    -0.26
    æŀľæĸŃ
    -0.25
     market
    -0.25
    wh
    -0.25
     com
    -0.24
     Dispatch
    -0.24
    heads
    -0.24
    POSITIVE LOGITS
     <![
    0.29
    åѤç«ĭ
    0.28
     tslint
    0.26
     Glover
    0.26
    åı£
    0.26
    uslim
    0.25
    DMIN
    0.25
    主ä¹ī
    0.25
    åĺ´
    0.25
     (![
    0.24
    Activations Density 4.002%

    No Known Activations