© 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. 12-TRANSCODER-HP
    7. 21975
    Prev
    Next
    INDEX
    Explanations

    different writing styles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    iamond
    -0.26
    errick
    -0.25
    ãĥģãĥ£ãĥ³
    -0.25
    /Private
    -0.25
     arrayOf
    -0.24
    .hu
    -0.24
     extr
    -0.24
     ****************************************
    -0.24
     spans
    -0.24
     *[
    -0.24
    POSITIVE LOGITS
    wal
    0.28
    åľ¨è¿ĩ渡
    0.26
    NotEmpty
    0.26
    ç¦ģå¿Į
    0.25
    ptype
    0.25
    æĽ´ä¸º
    0.25
    =("
    0.24
    ä¸įä»ħ
    0.24
    åĴ½
    0.24
    æ§IJ
    0.24
    Activations Density 0.000%

    No Known Activations