© 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. 129451
    Prev
    Next
    INDEX
    Explanations

    to

    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
    èĬ
    -0.28
     Campbell
    -0.27
    åģļå·¥
    -0.27
    åįķåįķ
    -0.26
    cope
    -0.26
     materially
    -0.26
    autom
    -0.26
     od
    -0.25
    çĶ¨æīĭ
    -0.25
    ully
    -0.25
    POSITIVE LOGITS
    æĹ¥åľ¨
    0.28
    -post
    0.27
    owards
    0.27
    梦æĥ³
    0.26
    tent
    0.26
    ton
    0.26
    mö
    0.26
     catches
    0.25
     kÃŃnh
    0.25
    enor
    0.25
    Activations Density 5.424%

    No Known Activations