© 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. 20791
    Prev
    Next
    INDEX
    Explanations

    undergoing or experiencing change

    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
     liá»ĩt
    -0.10
    汩
    -0.09
    æķ¬è¯·
    -0.09
    æľīæĿ¡ä»¶çļĦ
    -0.09
    å±ħ
    -0.09
    createView
    -0.09
    æŁ¥çľĭ详æĥħ
    -0.09
     Dw
    -0.09
    è¡¥
    -0.08
    æīĵéĢłåĩº
    -0.08
    POSITIVE LOGITS
    ç»ıåİĨ
    0.17
    ç»ıåİĨäºĨ
    0.14
    ç¶ĵæŃ·
    0.14
    éģŃéģĩ
    0.12
    åıijçĶŁäºĨ
    0.11
     undergo
    0.11
    éļ¾è¿ĩ
    0.11
     experiences
    0.11
    éĿ¢ä¸´
    0.10
    éģŃåıĹ
    0.10
    Activations Density 0.083%

    No Known Activations