© 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. 23424
    Prev
    Next
    INDEX
    Explanations

    from X to X

    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
    ãĤ¾
    -0.10
    çĺĹ
    -0.09
    绣
    -0.09
    èľ¡
    -0.09
    åľ¨æѤ
    -0.08
    ãĤ¸ãĥ§ãĥ³
    -0.08
    çļĦåĽłç´ł
    -0.08
    æľ¬ç«Ļ
    -0.08
    对æłĩ
    -0.08
    çĦ¶æĺ¯
    -0.08
    POSITIVE LOGITS
    æijĩ
    0.10
    ä¹ĭéĹ´çļĦ
    0.09
    ä¹ĭéĸĵ
    0.09
    ä¹ĭéĹ´
    0.09
     à¹Ĩ
    0.09
    ë§Īëĭ¤
    0.09
    åįģåĩłå¹´
    0.09
    -to
    0.09
    æ´¥
    0.09
    ä¸įä¸Ģæł·
    0.08
    Activations Density 0.047%

    No Known Activations