© 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. 33633
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by common words

    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
    aggio
    -0.09
    çĭĤ欢
    -0.08
    æľĢéĢĤåIJĪ
    -0.08
    çķĻ
    -0.08
    é£İåı£
    -0.08
     famously
    -0.08
    _evt
    -0.07
    ä¸įæİĴéĻ¤
    -0.07
    éĤ£æ®µ
    -0.07
    æľĢåıĹ
    -0.07
    POSITIVE LOGITS
    åŁºæľ¬ä¿¡æģ¯
    0.11
    åľ¨æĪijçľĭæĿ¥
    0.10
    åŁºæľ¬æĥħåĨµ
    0.10
    Reviewer
    0.10
    ä¸Ģå¦ĤæĹ¢å¾Ģ
    0.10
    æĭ¿èµ·
    0.10
    让æĪij
    0.10
    ä¸ĢåĪĻ
    0.09
    ä¸Ģå¦Ĥ
    0.09
    åĬ³ç´¯
    0.09
    Activations Density 0.210%

    No Known Activations