© 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. 108081
    Prev
    Next
    INDEX
    Explanations

    Programming and data analysis

    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
    亲
    -0.28
    Reuse
    -0.27
     mould
    -0.25
    getVar
    -0.25
     illeg
    -0.25
     necessarily
    -0.25
    親
    -0.25
    æĸ°å¼Ģ
    -0.24
    Viol
    -0.23
     perc
    -0.23
    POSITIVE LOGITS
    Acts
    0.29
    loh
    0.27
    éĶı
    0.26
     contrast
    0.25
    åĺĽ
    0.25
     éc
    0.24
     unit
    0.24
    á»®
    0.23
     Baghd
    0.23
     Acts
    0.23
    Activations Density 1.697%

    No Known Activations