© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 9-TRANSCODER-HP
    7. 29597
    Prev
    Next
    INDEX
    Explanations

    Yale University

    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
    Not in Any Lists

    No Comments

    Negative Logits
    awn
    -0.26
    éĮ¯
    -0.26
    bose
    -0.25
    æŃ£å¸¸ä½¿çĶ¨
    -0.25
     Wise
    -0.25
     Literal
    -0.25
    çĭ¬ä¸Ģ
    -0.25
    _LITERAL
    -0.24
     litter
    -0.24
    ewise
    -0.24
    POSITIVE LOGITS
     ALIGN
    0.29
     reinforcing
    0.28
    corner
    0.28
    å±Ī
    0.27
    度
    0.26
    åĪĨæķ°
    0.26
     confirming
    0.25
     Eli
    0.25
    æĽ²
    0.25
    æŃ£å¼ı
    0.25
    Activations Density 0.615%

    No Known Activations