© 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. 64338
    Prev
    Next
    INDEX
    Explanations

    GAS

    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
    riminal
    -0.28
    ouser
    -0.27
    æľįåĬ¡æ°´å¹³
    -0.25
    人æ°ij
    -0.25
     terminates
    -0.25
    Whitespace
    -0.25
     Zus
    -0.24
     terminating
    -0.24
    atics
    -0.24
     Baths
    -0.24
    POSITIVE LOGITS
    ç½Ĺæĸ¯
    0.28
    è°¤
    0.27
    elsey
    0.26
    orris
    0.26
     dubious
    0.25
    å°±å¼Ģå§ĭ
    0.25
     Gle
    0.24
     dyn
    0.24
    åŁł
    0.24
    è¾Ļ
    0.24
    Activations Density 17.664%

    No Known Activations