© 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. 5816
    Prev
    Next
    INDEX
    Explanations

    hearing or sound

    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
    ÑģÑĭл
    -0.10
    ogle
    -0.09
    讲究
    -0.09
    TRA
    -0.09
    æĹłåı¯
    -0.09
    订éĺħ
    -0.08
    кÑĥп
    -0.08
    portun
    -0.08
    SHARE
    -0.08
     Vulcan
    -0.08
    POSITIVE LOGITS
    æ¹Ľ
    0.10
    ä¸Ģ声
    0.10
    åĵį
    0.10
     Freeze
    0.10
    åĩŃ
    0.09
     Nap
    0.09
    oused
    0.09
     ÑĦоÑĢ
    0.09
    好æ¶Īæģ¯
    0.09
    鸣
    0.09
    Activations Density 0.206%

    No Known Activations