© 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. 37056
    Prev
    Next
    INDEX
    Explanations

    by and location phrases

    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
    馥
    -0.11
    оде
    -0.10
    ISR
    -0.09
    è·Ŀ
    -0.09
    ä¸į让
    -0.09
    IGHT
    -0.09
    çľ¼çļ®
    -0.09
    æİĮ
    -0.09
    轩
    -0.09
    ä¸įåľ¨ä¹İ
    -0.09
    POSITIVE LOGITS
    åģļ个
    0.09
    ford
    0.09
    交éĢļæŀ¢çº½
    0.09
    äºŃ
    0.09
    ETA
    0.08
    glob
    0.08
     dw
    0.08
    精彩
    0.08
    dw
    0.08
    ACES
    0.08
    Activations Density 0.012%

    No Known Activations