© 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. 31793
    Prev
    Next
    INDEX
    Explanations

    accounting for percentages

    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
    幺
    -0.10
    è¿ĩ硬
    -0.10
    asha
    -0.09
    èľ»
    -0.09
    ç¾ŀ
    -0.09
    çļĦèģĮä¸ļ
    -0.09
    è±ĨèħIJ
    -0.09
    .addHandler
    -0.09
    åŃķæľŁ
    -0.09
    åĽ¤
    -0.09
    POSITIVE LOGITS
    åįł
    0.28
    åįłæ¯Ķ
    0.23
    ä½Ķ
    0.21
    约åįł
    0.20
    åįłæį®äºĨ
    0.18
    åįłæį®
    0.17
    æ¯Ķéĩį
    0.15
     chiếm
    0.14
    ä¸ĢåįĬ
    0.13
    æ¯Ķä¾ĭ
    0.13
    Activations Density 0.162%

    No Known Activations