© 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. 108014
    Prev
    Next
    INDEX
    Explanations

    Technical/scientific writing

    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
    виз
    -0.29
    éĥ¤
    -0.29
    ORB
    -0.27
    lä
    -0.26
    è¡·
    -0.26
    ç±»åŀĭçļĦ
    -0.26
    BOSE
    -0.24
    ç±»åŀĭ
    -0.24
    IOUS
    -0.24
    鸪
    -0.24
    POSITIVE LOGITS
    èĩªçĦ¶
    0.30
     natural
    0.30
     Equ
    0.28
     conception
    0.28
     cosmic
    0.27
    fs
    0.27
    éĩĬ
    0.27
    æģ
    0.27
    addListener
    0.26
     mains
    0.26
    Activations Density 61.124%

    No Known Activations