© 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. 21958
    Prev
    Next
    INDEX
    Explanations

    easy thing

    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
    æľįåĬ¡æ°´å¹³
    -0.09
    èĢĮä¸įæĺ¯
    -0.09
    éĴĵé±¼
    -0.09
    boom
    -0.09
    æĽ´èĥ½
    -0.08
    循
    -0.08
    ä¸įèĩ³äºİ
    -0.08
    涵
    -0.08
    çĥ¦
    -0.08
    çªģ
    -0.08
    POSITIVE LOGITS
     nor
    0.16
    èĢĮæĺ¯
    0.16
    nor
    0.12
    Nor
    0.12
    ä¹Łä¸įæĺ¯
    0.11
     sondern
    0.11
     Nor
    0.11
    ä¹Łæ²¡æľī
    0.10
    cheap
    0.10
    ä¹Łä¸į
    0.10
    Activations Density 0.017%

    No Known Activations