© 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. 10135
    Prev
    Next
    INDEX
    Explanations

    code and forums

    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
    èĶº
    -0.11
    æ¦Ħ
    -0.10
    佬
    -0.10
    å¿«æĿ¥
    -0.10
    ä¸į妨
    -0.10
    æĥħæĻ¯
    -0.09
    æľŁ
    -0.09
     choÄĩ
    -0.09
    æĥĬå¥ĩ
    -0.09
    æĶ¹éĿ©å§Ķ
    -0.09
    POSITIVE LOGITS
    ä½łè¯´
    0.11
    uras
    0.08
     gamm
    0.08
    è¬ĩ
    0.08
    说è¿ĩ
    0.08
     earlier
    0.08
    è¡ĮåĬ¨è®¡åĪĴ
    0.07
    é¢ĺ主
    0.07
     Wagner
    0.07
     Ki
    0.07
    Activations Density 0.019%

    No Known Activations