© 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. 24330
    Prev
    Next
    INDEX
    Explanations

    ending with punctuation or conjunctions

    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
    并ä¸İ
    -0.09
    овоÑĢ
    -0.08
    .demo
    -0.07
     âĢķ
    -0.07
    åIJĪ
    -0.07
    нима
    -0.07
    æľīåĪ©äºİ
    -0.07
    ?
    -0.07
    [
    -0.07
    anje
    -0.06
    POSITIVE LOGITS
    麽
    0.11
    强迫
    0.11
    çŀŃ解並
    0.10
    olen
    0.10
    ç»
    0.09
    åħĪ导
    0.09
    使çĶ¨ç¶²è·¯
    0.09
    ilded
    0.09
    oga
    0.09
    æĻ°
    0.09
    Activations Density 0.799%

    No Known Activations