© 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. 41372
    Prev
    Next
    INDEX
    Explanations

    pink

    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
    çłĶ究éĻ¢
    -0.34
    æĹ©å°±
    -0.29
     pBuffer
    -0.25
    гÑĢад
    -0.25
     nerd
    -0.23
     accumulating
    -0.23
    odule
    -0.23
    çļĦæĦıä¹ī
    -0.23
    çŃīå¥ĸ
    -0.23
     earliest
    -0.23
    POSITIVE LOGITS
    å±¥
    0.30
     KO
    0.28
    åģ¶
    0.27
    é«ĺä½į
    0.27
    GCC
    0.26
    èľķ
    0.26
    ä¸įåIJĮçļĦ
    0.26
    ,GL
    0.25
    ullah
    0.24
    交
    0.24
    Activations Density 0.125%

    No Known Activations