© 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. 26310
    Prev
    Next
    INDEX
    Explanations

    audio signal and 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
    Negative Logits
    ä¸ŃéĢĶ
    -0.10
    å±ķ示äºĨ
    -0.09
    it
    -0.08
    0
    -0.08
    3
    -0.08
    å®Īä½ı
    -0.08
    4
    -0.08
    ListItem
    -0.08
    æĻĸ
    -0.08
    ç°¿
    -0.08
    POSITIVE LOGITS
    å£°éŁ³
    0.14
    çļĦå£°éŁ³
    0.12
    缺失
    0.11
    声éģĵ
    0.11
    èģ²éŁ³
    0.10
     Sound
    0.10
     sound
    0.10
     Muk
    0.10
    ç«ĭä½ĵ
    0.10
    .sound
    0.10
    Activations Density 0.064%

    No Known Activations