© 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. 41673
    Prev
    Next
    INDEX
    Explanations

    Names

    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
     Prim
    -0.30
    å»·
    -0.29
     lis
    -0.28
    gie
    -0.28
    ipp
    -0.27
    prim
    -0.27
    Prim
    -0.26
     philosophy
    -0.26
     fat
    -0.25
    getWindow
    -0.24
    POSITIVE LOGITS
    âĢ¢↵↵
    0.28
    iterated
    0.27
    ä¸ĢåIJį
    0.26
     Bombay
    0.26
    åīįæīĢæľª
    0.26
    ¢
    0.24
    æ¤Ł
    0.24
     reservations
    0.24
    SCRIBE
    0.23
    ello
    0.23
    Activations Density 0.306%

    No Known Activations