© 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. 48352
    Prev
    Next
    INDEX
    Explanations

    anytime soon

    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
    TouchEvent
    -0.10
    å±ĬæŶ
    -0.09
    æļĤæŶ
    -0.09
    ä¸ĭåij¨
    -0.09
    ä¸Ŀ
    -0.09
    åĽ½ç±į
    -0.08
    åĪ°æŶåĢĻ
    -0.08
    æļĤ
    -0.08
    umeric
    -0.08
     Koch
    -0.08
    POSITIVE LOGITS
    hg
    0.10
     Äijá»Ŀi
    0.08
    çĦ¦
    0.08
    åĴİ
    0.08
    è´´å¿ĥ
    0.08
    دÙĪ
    0.08
    åĨĴ
    0.08
    亮
    0.08
    æĻı
    0.08
    éĢĴ
    0.08
    Activations Density 0.002%

    No Known Activations