© 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. 39554
    Prev
    Next
    INDEX
    Explanations

    stop words

    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
    CEPT
    -0.28
    lock
    -0.28
     lat
    -0.28
    ãĤªãĥ³
    -0.26
    -rock
    -0.26
    鼷
    -0.26
    esch
    -0.25
    odash
    -0.25
    HEST
    -0.25
    ERM
    -0.25
    POSITIVE LOGITS
    ä¹Łåı¯
    0.27
    èĢģ大
    0.26
    ä¹Łåı¯ä»¥
    0.26
    elman
    0.25
     emiss
    0.24
     adel
    0.24
     /\.
    0.24
    æĬĺåıł
    0.24
    åıijä½ľ
    0.24
    é©®
    0.24
    Activations Density 7.861%

    No Known Activations