© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 142523
    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
    Negative Logits
    åIJİç»Ń
    -0.28
    æľ¬è´¨
    -0.28
    лаÑĤ
    -0.26
    atis
    -0.26
    yan
    -0.24
    éĵ
    -0.24
    ä¸ĭ
    -0.24
    åľ¨æѤ
    -0.24
     remaining
    -0.24
    èīº
    -0.24
    POSITIVE LOGITS
    æĪĸå°Ĩ
    0.28
    çĶļèĩ³æĺ¯
    0.27
    ä»Ģä¹ĪåİŁåĽł
    0.26
    帻
    0.25
    èĭ«
    0.24
    among
    0.24
    éķľå¤´
    0.24
     eens
    0.23
     serialize
    0.23
    rients
    0.23
    Activations Density 10.992%

    No Known Activations

    This feature has no known activations.