© 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. 107187
    Prev
    Next
    INDEX
    Explanations

    Request or instructions

    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
    åı¦ä¸Ģç§į
    -0.29
    orted
    -0.28
    å°±å¿ħé¡»
    -0.27
    å¢ŀéĩı
    -0.27
    éĺĻ
    -0.26
    å°±éľĢè¦ģ
    -0.26
    berries
    -0.26
    示èĮĥåŁºåľ°
    -0.25
    æĽ´å¥½çļĦ
    -0.25
    hell
    -0.25
    POSITIVE LOGITS
    æŁ¥éªĮ
    0.26
    CTS
    0.25
     corpor
    0.25
    upt
    0.25
     instrument
    0.25
    对ç«ĭ
    0.25
    istan
    0.25
     harmon
    0.25
    ups
    0.24
     Tow
    0.24
    Activations Density 20.359%

    No Known Activations