© 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. 23915
    Prev
    Next
    INDEX
    Explanations

    immediately or on the spot

    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
    帮åĬ©ä¼ģä¸ļ
    -0.09
    èµĽåIJİ
    -0.09
    è¿ĩå¾Ĺ
    -0.09
    lag
    -0.09
    leading
    -0.09
     Jub
    -0.09
    èµĽ
    -0.09
    åı¦ä¸Ģæĸ¹éĿ¢
    -0.08
    æľĢåIJİä¸Ģ个
    -0.08
    à¹Ħà¸Ĺย
    -0.08
    POSITIVE LOGITS
    å½ĵåľº
    0.16
    ç«ĭåį³
    0.15
    ç«ĭåĪ»
    0.15
    å½ĵåį³
    0.13
    åį³æŶ
    0.12
     immediately
    0.12
    ç«ĭ马
    0.12
     اÙĦÙģÙĪر
    0.10
     ë°Ķë¡ľ
    0.10
    å½ĵä¸ĭ
    0.10
    Activations Density 0.061%

    No Known Activations