© 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. 141654
    Prev
    Next
    INDEX
    Explanations

    Measurements, amounts, limits

    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
    iculo
    -0.29
    quier
    -0.27
    è¦ģæĬĬ
    -0.27
    鬻
    -0.26
    \Redirect
    -0.26
    è¦ģåĬłå¼º
    -0.26
    çŃĶé¢ĺ
    -0.25
     CIM
    -0.25
    organic
    -0.25
    missive
    -0.24
    POSITIVE LOGITS
     Reference
    0.26
    æľ«
    0.26
     Soft
    0.25
    åĨ¬å¥¥
    0.25
    Reference
    0.25
    owo
    0.24
    bras
    0.24
    æĹ©æĻļ
    0.24
    ensburg
    0.24
    pt
    0.23
    Activations Density 12.124%

    No Known Activations