© 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. 5848
    Prev
    Next
    INDEX
    Explanations

    species name from studies is the

    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
    弥漫
    -0.08
    æ³īæ°´
    -0.08
    人çī©
    -0.08
    æ»Ĥ
    -0.08
    æ´Ĵ
    -0.08
     Frog
    -0.08
    çĢijå¸ĥ
    -0.08
    (by
    -0.08
    è¯Ł
    -0.08
    éĨª
    -0.07
    POSITIVE LOGITS
    ç§ijåѦçłĶ究
    0.12
    èĩªçĦ¶çķĮ
    0.11
    çī©ç§į
    0.11
    æłĸ
    0.11
    ç§ijåŃ¦å®¶
    0.11
    éĩİçĶŁ
    0.11
    çĶŁæ´»åľ¨
    0.11
    饲åħ»
    0.10
    ç¹ģæ®ĸ
    0.10
    被æįķ
    0.10
    Activations Density 0.257%

    No Known Activations