© 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. 64188
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     minimal
    -0.27
     Dorm
    -0.27
    mond
    -0.27
    Bomb
    -0.26
    æľīä¸Ģå®ļ
    -0.26
     setC
    -0.25
    æĪĺåľºä¸Ĭ
    -0.25
    >c
    -0.25
    +c
    -0.25
    Cascade
    -0.25
    POSITIVE LOGITS
    obili
    0.29
    åıĺæĽ´
    0.26
    Ticker
    0.26
    ủ
    0.25
    æĦ§
    0.24
    ANGER
    0.24
    èĦ²
    0.24
     zusätzlich
    0.23
    queued
    0.23
    vary
    0.23
    Activations Density 3.144%

    No Known Activations

    This feature has no known activations.