© 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. 49425
    Prev
    Next
    INDEX
    Explanations

    I know what will happen

    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
    åıªä¸º
    -0.09
    åĿĩ为
    -0.08
    çªģåĩº
    -0.08
     /************************************************************************
    -0.08
    isz
    -0.08
     Truly
    -0.08
    pé
    -0.08
    è¿Ļæł·ä¸ĢæĿ¥
    -0.07
    æľ¬æĿ¥å°±
    -0.07
    羣åĪĩ
    -0.07
    POSITIVE LOGITS
    izr
    0.10
    æĻļå¹´
    0.10
    æīģ
    0.09
    uhan
    0.09
    signals
    0.09
    主å¸Ń
    0.09
    ä¸İä¸ŃåĽ½
    0.09
    èĨĽ
    0.09
    AKER
    0.08
    ì¶ķ
    0.08
    Activations Density 0.060%

    No Known Activations