© 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. 9-TRANSCODER-HP
    7. 29335
    Prev
    Next
    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     пока
    -0.28
     Inspector
    -0.26
    uche
    -0.25
    åıĸ
    -0.25
    åħ´
    -0.25
    æ·±
    -0.25
    apos
    -0.24
     Fire
    -0.24
    fire
    -0.23
     Exc
    -0.23
    POSITIVE LOGITS
     mé
    0.26
    åĭ¤
    0.26
    å°ģ建
    0.25
    秣
    0.24
    angled
    0.24
    è¿¥
    0.23
    è¡Įä¸ļåįıä¼ļ
    0.23
    [axis
    0.23
    å¿ĥä¸Ń
    0.23
    åĬĽåѦ
    0.23
    Activations Density 3.576%

    No Known Activations