© 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. 2736
    Prev
    Next
    INDEX
    Explanations

    is definitely the

    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
    çĩ®
    -0.10
    è¶Ĭæĺ¯
    -0.10
     helf
    -0.09
    诸å¦Ĥ
    -0.09
     Haz
    -0.09
    å°±è¶Ĭ
    -0.09
    éĩ
    -0.09
    WINDOWS
    -0.08
    è¶ĬæĿ¥
    -0.08
    æľīçļĦ
    -0.08
    POSITIVE LOGITS
    ä¸įå±ŀäºİ
    0.15
    ä¹Łæĺ¯ä¸Ģç§į
    0.15
    ä¹Łç®Ĺæĺ¯
    0.15
    ç®Ĺæĺ¯
    0.14
    ä¹Łç®Ĺ
    0.12
    èĻ½çĦ¶æĺ¯
    0.12
    å±ŀäºİ
    0.12
    ä¹Łæĺ¯ä¸Ģ个
    0.12
    ä¸įç®Ĺ
    0.12
    屬æĸ¼
    0.12
    Activations Density 0.160%

    No Known Activations