© 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. 29326
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    éĻĽ
    -0.30
    _parms
    -0.27
    Criteria
    -0.26
    妩
    -0.26
    票
    -0.25
    nees
    -0.25
    _criteria
    -0.25
     Curt
    -0.24
    ero
    -0.24
    表åĨ³
    -0.24
    POSITIVE LOGITS
    ress
    0.29
    ä¿Ĺ
    0.28
    ÙħاÙĨ
    0.27
    çĽ
    0.27
    è¿Ľ
    0.25
    æŃ¢æįŁ
    0.25
    飬
    0.25
    éĿĻ
    0.25
    çŃĭ
    0.25
    çĽĺ
    0.24
    Activations Density 3.019%

    No Known Activations