© 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. 50107
    Prev
    Next
    INDEX
    Explanations

    non- prefix

    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
    å¹²èĦĨ
    -0.09
    èĢĮä¸į
    -0.08
    ä¸įå¤Ł
    -0.08
    è¿ĺæĺ¯ä¼ļ
    -0.08
    ÑĤÑı
    -0.08
    è¿ĺä¸įå¤Ł
    -0.08
    AWN
    -0.08
     ÑĩÑĥÑĤÑĮ
    -0.08
    anter
    -0.08
    anne
    -0.08
    POSITIVE LOGITS
    çļĦåīįæıIJä¸ĭ
    0.10
    æĦı大
    0.10
    åı£æ°Ķ
    0.10
    çļĦåİŁåĪĻ
    0.09
    çļĦåĽŀçŃĶ
    0.09
    éĥ½åĸľæ¬¢
    0.09
    ibus
    0.09
    第ä¸Ģ家
    0.09
    èŀºæĹĭ
    0.09
     Gat
    0.09
    Activations Density 0.108%

    No Known Activations