© 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. 63952
    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
    ocks
    -0.29
    idi
    -0.28
     ded
    -0.27
    åĨĻ
    -0.26
    icer
    -0.25
     å¾
    -0.25
    å¹³åĿ¦
    -0.25
    ute
    -0.24
     perfect
    -0.24
    to
    -0.24
    POSITIVE LOGITS
    å¤ı
    0.27
    fills
    0.26
    Sys
    0.25
    å·²ç»ıæľīäºĨ
    0.25
    æĸ°éĹ»åıijå¸ĥ
    0.25
     honors
    0.25
    è®´
    0.24
    åıĹåĪ°äºĨ
    0.24
    çĥĥ
    0.23
    anas
    0.23
    Activations Density 1.890%

    No Known Activations

    This feature has no known activations.