© 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. 129033
    Prev
    Next
    INDEX
    Explanations

    dates

    np_max-act · gemini-2.0-flash
    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
    ipmap
    -0.26
    cobra
    -0.25
     achie
    -0.24
     nargin
    -0.24
    éĥ¨åī¯
    -0.24
    åįĸåľº
    -0.24
    /goto
    -0.23
    è¿Ļ个è¯į
    -0.23
    unfold
    -0.23
    èij±
    -0.23
    POSITIVE LOGITS
     nonetheless
    0.28
     nevertheless
    0.28
    è·¯è¿ĩ
    0.26
    åħ¨çIJĥåĮĸ
    0.25
    Dash
    0.25
    edar
    0.24
     partition
    0.23
    _distribution
    0.23
     equip
    0.23
    RS
    0.23
    Activations Density 15.507%

    No Known Activations