© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36329
    Prev
    Next
    INDEX
    Explanations

    whether it

    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
    ED
    -0.08
    ä¸į幸
    -0.08
    æĺ¯å¦Ĥä½ķ
    -0.07
    ãĤĭãĤĤãģ®
    -0.07
    -or
    -0.07
    çļĦéŃħåĬĽ
    -0.07
    åıªä¸įè¿ĩæĺ¯
    -0.07
     [
    -0.07
    ãģªãĤĤãģ®
    -0.07
     demean
    -0.07
    POSITIVE LOGITS
    ampie
    0.11
    棹
    0.10
    çªĴ
    0.10
    è·
    0.10
     ÐIJлекÑģан
    0.10
    usz
    0.10
    arshal
    0.09
    éĢ¢
    0.09
    èĩ³äºİ
    0.09
    Ø£Ùĩد
    0.09
    Activations Density 0.300%

    No Known Activations