© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7996
    Prev
    Next
    INDEX
    Explanations

    leaving behind

    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
    æµģ浪
    -0.10
    erer
    -0.10
    æ¸ł
    -0.09
    æĤŃ
    -0.09
    åı²ä¸ĬæľĢ
    -0.09
    éĤ»å±ħ
    -0.09
    _FLASH
    -0.09
    bare
    -0.09
    å¿ħè¦ģ
    -0.09
    大åݦ
    -0.09
    POSITIVE LOGITS
    çķĻä¸ĭ
    0.17
    çķĻä¸ĭäºĨ
    0.16
    éģĹçķĻ
    0.16
    çķĻä¸ĭæĿ¥
    0.16
    çķĻ
    0.15
    çķĻåľ¨
    0.13
    çķĻç»Ļ
    0.13
    éģĹæ¼ı
    0.12
     Leave
    0.12
    æ®ĭçķĻ
    0.12
    Activations Density 0.049%

    No Known Activations