© 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. 19516
    Prev
    Next
    INDEX
    Explanations

    requesting information or action

    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
    å·²ç»ıæľīäºĨ
    -0.09
    éĽı
    -0.09
    azon
    -0.09
    çģµæĦŁ
    -0.09
    æį¢äºĨ
    -0.09
    è¦ģçĶ¨
    -0.09
    è¿ĺæĺ¯è¦ģ
    -0.09
    è¿ĺå°Ĩ
    -0.09
    æľĢåħ³éĶ®çļĦ
    -0.09
    è¿ĺä¸įæĺ¯
    -0.09
    POSITIVE LOGITS
     submitted
    0.11
    submitted
    0.11
     IRequest
    0.10
    è¾ĵåħ¥
    0.09
     requested
    0.09
    请æ±Ĥ
    0.09
    举
    0.09
    aska
    0.09
    ãģķãģĪ
    0.09
     choices
    0.09
    Activations Density 0.156%

    No Known Activations