© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 16617
    Prev
    Next
    INDEX
    Explanations

    hesitation sounds

    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
    Negative Logits
    andy
    -0.09
    åĺ»åĺ»
    -0.09
    anke
    -0.08
    chet
    -0.08
    ypes
    -0.08
    ÑĪин
    -0.08
    å¿ĥæĢĿ
    -0.08
    带åĪ°
    -0.08
    무
    -0.08
     оÑģ
    -0.07
    POSITIVE LOGITS
    çĶµè§Ĩæľº
    0.09
    ä»ĸ们æĺ¯
    0.09
    è¦ģæĬĬ
    0.09
    ä¸įç®¡ä½ł
    0.08
    åĩłä¸ªäºº
    0.08
    è§Ħ模以ä¸Ĭ
    0.08
    éric
    0.08
    èłĸ
    0.08
    棹
    0.08
    бл
    0.08
    Activations Density 0.005%

    No Known Activations