© 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. 58445
    Prev
    Next
    INDEX
    Explanations

    time durations

    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
    åĩij
    -0.11
    è¯Ĭ
    -0.10
    å±ķæ¼Ķ
    -0.10
    æĻ°
    -0.10
    çļĦåīįæıIJä¸ĭ
    -0.09
    æľ¬èº«å°±æĺ¯
    -0.09
    å¨ĺ家
    -0.09
    çļĦè¿ĩç¨ĭä¸Ń
    -0.09
    ä»ĬåIJİ
    -0.09
    IPP
    -0.09
    POSITIVE LOGITS
     being
    0.08
    缸äºĴ
    0.08
    讵
    0.08
    å¤ļå¹´çļĦ
    0.08
    ä¸Ģ个å¤ļ
    0.08
     lÆ°ng
    0.08
    æĹłæĥħ
    0.07
    noon
    0.07
    æīįçŁ¥éģĵ
    0.07
     dic
    0.07
    Activations Density 0.058%

    No Known Activations