© 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. 23004
    Prev
    Next
    INDEX
    Explanations

    I think

    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
    çľ¼è§Ĵ
    -0.09
    uns
    -0.09
    icy
    -0.09
    ä¸įå¿ĺ
    -0.09
    dag
    -0.08
    .foundation
    -0.08
    å¿įä¸įä½ı
    -0.08
    elin
    -0.08
    祸
    -0.08
    念
    -0.08
    POSITIVE LOGITS
    è¿Ļæīįæĺ¯
    0.11
    åľ¨èģĮ
    0.09
    çĶį
    0.09
    çļĦåģļæ³ķ
    0.09
    è¿Ļå°±æĺ¯
    0.09
    è¿Ļ个éĹ®é¢ĺ
    0.09
    hem
    0.09
    aylor
    0.09
    дин
    0.08
    æĽ´ä½ķåĨµ
    0.08
    Activations Density 0.020%

    No Known Activations