© 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. 129770
    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
    ukan
    -0.26
    agar
    -0.26
     drinking
    -0.26
     Ashton
    -0.25
    .utility
    -0.24
    çŁ¿æ³īæ°´
    -0.24
    vig
    -0.24
    é¾Ħ
    -0.24
    spread
    -0.24
     spread
    -0.23
    POSITIVE LOGITS
     Atlantis
    0.28
    çļĦéĹ®é¢ĺ
    0.26
    éĢģç»Ļ
    0.26
     validationResult
    0.24
    dden
    0.24
    æĹ¶è¡¨ç¤º
    0.24
     trusts
    0.24
    è¿ĽæŃ¥
    0.24
    误åĮº
    0.24
    phalt
    0.24
    Activations Density 0.735%

    No Known Activations

    This feature has no known activations.