© 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. 10923
    Prev
    Next
    INDEX
    Explanations

    calendar months and time periods

    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
    åĪ°æŶåĢĻ
    -0.11
    å±ĬæŶ
    -0.11
    æľªæĿ¥çļĦ
    -0.10
    广çĶµ
    -0.09
    hand
    -0.09
    é¢Ĭ
    -0.09
    é»į
    -0.08
    older
    -0.08
     someday
    -0.08
    毯
    -0.08
    POSITIVE LOGITS
     compared
    0.11
    缸æ¯Ķ
    0.11
    æ¯Ķèµ·
    0.10
    çŁŃçŁŃ
    0.09
    æĬ¥åijĬæĺ¾ç¤º
    0.09
    åŁİå¸Ĥ群
    0.09
    è¿«
    0.09
    å±ŀå®ŀ
    0.08
    çĽijè§Ĩ
    0.08
    redo
    0.08
    Activations Density 0.062%

    No Known Activations