© 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. 40944
    Prev
    Next
    INDEX
    Explanations

    programming

    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
     Bin
    -0.25
    çĪ±
    -0.25
     passed
    -0.25
    æIJĶ
    -0.24
    enal
    -0.24
    Tk
    -0.24
    cheng
    -0.24
    stras
    -0.24
     sic
    -0.24
    éĴĵé±¼
    -0.24
    POSITIVE LOGITS
    æĹ¥è®¯
    0.31
    ableObject
    0.29
    âĢ¦↵↵↵↵
    0.28
    宣
    0.26
    LAY
    0.25
    ä½ľèĢħæľ¬äºº
    0.24
    ColorBrush
    0.24
    annes
    0.24
    IGHLIGHT
    0.24
    ç½ķ
    0.24
    Activations Density 0.131%

    No Known Activations