© 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. 61335
    Prev
    Next
    INDEX
    Explanations

    directory, svn, platforms, range

    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
    没éĶĻ
    -0.10
    ä¸įèĩ³äºİ
    -0.10
    ä¸įå®Į
    -0.10
     kicks
    -0.10
    wald
    -0.10
    åħ¬æŃ£
    -0.09
    被害
    -0.09
    çĪ»
    -0.09
    æķ´ä¸ªäºº
    -0.09
    èĢĮä¸įæĺ¯
    -0.09
    POSITIVE LOGITS
    ä»»ä½ķå½¢å¼ı
    0.16
    æľīä»»ä½ķ
    0.15
    éĻ¤éĿŀ
    0.14
    unless
    0.13
     unless
    0.13
    ä¹Łä¸įèĥ½
    0.12
     nor
    0.11
    oji
    0.10
    except
    0.10
    å¾Ĺ太
    0.10
    Activations Density 0.143%

    No Known Activations