© 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. 40621
    Prev
    Next
    INDEX
    Explanations

    fermentation and food

    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
    oma
    -0.29
    æ¢Ĺ
    -0.26
    rise
    -0.26
     desc
    -0.25
    ilog
    -0.25
     getchar
    -0.25
     Weston
    -0.24
     res
    -0.23
     autoc
    -0.23
    å¿«
    -0.23
    POSITIVE LOGITS
    itarian
    0.27
    ForResult
    0.26
    èģ¯åIJĪ
    0.26
    åŁĴ
    0.25
    äºĮåŃĹ
    0.25
    æĸ¹éĿ¢çļĦ
    0.24
    ately
    0.24
    kop
    0.24
     rag
    0.24
    设计çIJĨ念
    0.24
    Activations Density 0.091%

    No Known Activations