© 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. 107631
    Prev
    Next
    INDEX
    Explanations

    Code/Warnings/Legal text

    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
     Kab
    -0.28
    举æĬ¥çĶµè¯Ŀ
    -0.27
     CCP
    -0.27
    éĻ¨
    -0.25
    stitutions
    -0.25
    è·ĭ
    -0.24
    èŃ¦ç¤º
    -0.24
     |--------------------------------------------------------------------------↵
    -0.24
     cheated
    -0.24
    ãĢģ“
    -0.24
    POSITIVE LOGITS
    çŃĽ
    0.27
     Overflow
    0.26
     week
    0.26
    ULO
    0.26
    yr
    0.25
    UDO
    0.25
    å¡«
    0.25
     overflow
    0.25
     lo
    0.24
    æĿĵ
    0.24
    Activations Density 5.002%

    No Known Activations