© 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. 14-TRANSCODER-HP
    7. 40762
    Prev
    Next
    INDEX
    Explanations

    method

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¼ī
    -0.30
    è§IJ
    -0.27
    äºĮ级
    -0.27
    าร
    -0.25
     gou
    -0.25
    _LL
    -0.24
     Lal
    -0.24
    ources
    -0.23
    oric
    -0.23
    ARGV
    -0.23
    POSITIVE LOGITS
    主æĮģ人
    0.35
    æĽ´å¤ļ
    0.29
    rust
    0.26
    -worker
    0.26
    迹
    0.25
    æīĢåľ¨
    0.25
    产
    0.24
     compounds
    0.24
    æĽ´å¤§
    0.24
    æīĢåľ¨çļĦ
    0.24
    Activations Density 0.062%

    No Known Activations