© 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. 34939
    Prev
    Next
    INDEX
    Explanations

    press release dateline

    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
    äºı
    -0.09
    å°Ŀ
    -0.09
    第ä¸ĢæĿ¡
    -0.08
    æŃ¤åŁºç¡Ģä¸Ĭ
    -0.08
    bearing
    -0.08
    订
    -0.08
    ä¼ĺåĬ¿
    -0.08
     Bates
    -0.08
    åģľä¸ĭ
    -0.08
    wap
    -0.08
    POSITIVE LOGITS
    æĻĶ
    0.10
    å¥Ń
    0.10
    æĭŃ
    0.09
    สาร
    0.09
    -worthy
    0.09
    è¾ħ
    0.09
     gim
    0.09
    åı£æ°Ķ
    0.09
    /mark
    0.09
    ceso
    0.08
    Activations Density 0.001%

    No Known Activations