© 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. 108100
    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
     lược
    -0.26
    äºĨä¸Ģæī¹
    -0.25
    rase
    -0.25
    äºĨä¸Ģåı¥
    -0.25
     esi
    -0.25
    å°±æĺ¯è¿Ļæł·
    -0.24
    ecs
    -0.24
    одеÑĢж
    -0.24
    resses
    -0.23
    ä¸Ģ次æĢ§
    -0.23
    POSITIVE LOGITS
    ting
    0.27
    ç¾İ好
    0.27
     sag
    0.27
    Ũ
    0.25
    ç¯ģ
    0.24
    ÑĢиÑĤ
    0.24
     gl
    0.24
    à°Ĺ
    0.24
     plugged
    0.24
    Meter
    0.24
    Activations Density 14.607%

    No Known Activations

    This feature has no known activations.