© 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. 14-TRANSCODER-HP
    7. 41738
    Prev
    Next
    INDEX
    Explanations

    Punctuation and code characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Dud
    -0.27
    CurrentUser
    -0.27
    沿éĢĶ
    -0.26
    éĹ»
    -0.26
    abouts
    -0.25
    éļıå¤Ħ
    -0.25
    ç½ijç»ľä¼łæĴŃ
    -0.25
    tps
    -0.24
    èµĤ
    -0.23
     Mits
    -0.23
    POSITIVE LOGITS
    OfFile
    0.27
    æĹłåĬ©
    0.25
     Oz
    0.25
    æ¯Ĺ
    0.24
    ç»ıæŁ¥
    0.24
    nte
    0.24
    birth
    0.24
    Ok
    0.24
    è¯ķè¡Į
    0.24
     realised
    0.23
    Activations Density 1.011%

    No Known Activations