© 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. 63575
    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
     vfs
    -0.30
     Vuex
    -0.29
    bsite
    -0.29
    quarters
    -0.28
    -Jan
    -0.26
    (Sql
    -0.26
    /hash
    -0.25
    ivant
    -0.25
    _Osc
    -0.25
    -quarters
    -0.25
    POSITIVE LOGITS
    好å¤Ħ
    0.32
    ä»Ģä¹Īåij¢
    0.29
     anything
    0.28
    prefix
    0.27
    abo
    0.27
    æľĢåIJİä¸Ģ次
    0.27
    åįĩ
    0.27
    åħī
    0.27
    LETE
    0.26
    ä»Ģä¹Īåı«
    0.25
    Activations Density 0.968%

    No Known Activations

    This feature has no known activations.