© 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. 107361
    Prev
    Next
    INDEX
    Explanations

    Auxiliary verbs

    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
    losing
    -0.31
    离åŃIJ
    -0.28
     Losing
    -0.28
    astery
    -0.28
    raph
    -0.27
    ivid
    -0.26
    .Attach
    -0.26
    -basket
    -0.26
    losure
    -0.26
    .imp
    -0.24
    POSITIVE LOGITS
     <!--[
    0.31
    Teacher
    0.29
    ea
    0.27
    si
    0.27
     tomorrow
    0.25
    xc
    0.25
     te
    0.24
    éĽĨä¸Ń
    0.24
     teacher
    0.24
     preparation
    0.24
    Activations Density 11.497%

    No Known Activations