© 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. 35296
    Prev
    Next
    INDEX
    Explanations

    activities may include

    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
    AsyncResult
    -0.10
    ä¸įçĶ¨
    -0.09
    iga
    -0.09
    é£İéĻ©ç®¡çIJĨ
    -0.08
    å¤ļå¹´çļĦ
    -0.08
    éĻ¤éĿŀ
    -0.08
    饴
    -0.08
    ç½ijéĢļ
    -0.08
    çļĦè¶ĭåĬ¿
    -0.08
    é³Ķ
    -0.08
    POSITIVE LOGITS
     rec
    0.09
    ä½Ĩä¸įéĻIJäºİ
    0.09
    å°±æĺ¯è¦ģ
    0.09
    uss
    0.09
    ä¾ĭå¦Ĥ
    0.09
    ingo
    0.08
    à¸ŀวà¸ģ
    0.08
    afil
    0.08
    çĵ´
    0.08
    æ¯Ķå¦Ĥ
    0.08
    Activations Density 0.112%

    No Known Activations