© 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. 29218
    Prev
    Next
    INDEX
    Explanations

    incorporate

    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
    éĽĨåĽ¢èĤ¡ä»½
    -0.31
    佶
    -0.26
    ÑĢеÑĪ
    -0.24
    æĪ¿ç§Ł
    -0.24
    ÃŃd
    -0.24
    å°ģéĶģ
    -0.24
     Tiles
    -0.23
    .bp
    -0.23
     hog
    -0.23
    ÑĤиÑĢ
    -0.23
    POSITIVE LOGITS
    iant
    0.34
     med
    0.30
    ursive
    0.26
    PubMed
    0.26
    _runner
    0.26
     pilot
    0.26
    Did
    0.26
     did
    0.26
     Dtype
    0.25
    uator
    0.25
    Activations Density 0.454%

    No Known Activations