© 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. 8101
    Prev
    Next
    INDEX
    Explanations

    program and application use

    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
    éĢĿ
    -0.11
    åŃļ
    -0.09
    å¸ĮæľĽå¤§å®¶
    -0.09
    åıĹ访èĢħ
    -0.09
    è§Ħ磩
    -0.08
    好çľĭçļĦ
    -0.08
    夫人
    -0.08
    buff
    -0.08
     COPYING
    -0.08
    æĻĸ
    -0.08
    POSITIVE LOGITS
     пÑĢогÑĢаммÑĭ
    0.10
     programs
    0.10
    è°Ī
    0.10
     program
    0.09
    _ask
    0.09
    ä¿¡èµĸ
    0.09
    泯
    0.09
    lore
    0.09
    åºĶçĶ¨ç¨ĭåºı
    0.09
     برÙĨ
    0.09
    Activations Density 0.835%

    No Known Activations