© 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. 19-TRANSCODER-HP
    7. 9666
    Prev
    Next
    INDEX
    Explanations

    Software/computer programs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    说æĺ¯
    -0.25
    对ä»ĸ们
    -0.25
    ä¸įä»ħè¦ģ
    -0.25
     rushed
    -0.24
    -ng
    -0.24
    åĸľ
    -0.24
    è¡¥
    -0.24
     exact
    -0.24
    让ä»ĸ们
    -0.23
    ìĸ´
    -0.23
    POSITIVE LOGITS
    alytics
    0.30
    .PropTypes
    0.26
    æĦı
    0.26
    åŁł
    0.26
    mites
    0.25
     ide
    0.25
    ,nil
    0.24
    缸åħ³åĨħ容
    0.24
    ä¸įå¼Ģ
    0.24
    icho
    0.24
    Activations Density 0.007%

    No Known Activations