© 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. 29101
    Prev
    Next
    INDEX
    Explanations

    article/excerpt

    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
     <![
    -0.28
    _KIND
    -0.27
    alam
    -0.27
    ortal
    -0.27
    ancing
    -0.25
    売ãĤĬ
    -0.23
    /edit
    -0.23
    oko
    -0.23
     waived
    -0.23
    oli
    -0.23
    POSITIVE LOGITS
    å¼Ģ端
    0.26
    çŃĴ
    0.26
     sideways
    0.25
    -links
    0.24
     Links
    0.24
    åĪĿ
    0.24
     Hil
    0.24
    links
    0.24
    æĸ°ä¸ĸ纪
    0.24
    ạn
    0.23
    Activations Density 1.024%

    No Known Activations