© 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. 41601
    Prev
    Next
    INDEX
    Explanations

    punctuation and symbols

    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
    adj
    -0.25
    çŃĽæŁ¥
    -0.25
    replacement
    -0.25
     lunches
    -0.24
    uche
    -0.24
    æĭ¥æĬ¤
    -0.23
    åĨį次
    -0.23
     payday
    -0.22
     Fucking
    -0.22
     pussy
    -0.22
    POSITIVE LOGITS
    åŃ
    0.27
    nos
    0.27
    phony
    0.26
     cons
    0.25
     giả
    0.25
    麻çĹ¹
    0.25
    LEX
    0.24
    maf
    0.23
     aspir
    0.23
     plant
    0.23
    Activations Density 0.921%

    No Known Activations