© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 63233
    Prev
    Next
    INDEX
    Explanations

    not to dismiss or underestimate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å°Ŀ
    -0.09
    æł¹æľ¬å°±ä¸į
    -0.09
    éĽĸ
    -0.09
    anh
    -0.09
    è¿ĺæľīä»Ģä¹Ī
    -0.09
     Kitt
    -0.09
    ç»´æĮģ
    -0.09
     suit
    -0.09
    èĻ½
    -0.08
    yon
    -0.08
    POSITIVE LOGITS
    /licenses
    0.10
    ç¬ĶèĢħ
    0.10
    è½»
    0.10
    ä½ľèĢħæľ¬äºº
    0.09
    æĺ¯ä¸ºäºĨ
    0.09
    GetInstance
    0.09
    /LICENSE
    0.09
    æıIJåĢ¡
    0.09
     hereby
    0.09
    说å¾Ĺ
    0.09
    Activations Density 0.034%

    No Known Activations