© 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. 26216
    Prev
    Next
    INDEX
    Explanations

    interjections and common speech fillers

    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
    æŀķ
    -0.10
    åij¼
    -0.10
    äºĨäºĽ
    -0.10
    æ´Ĺ礼
    -0.09
    秦çļĩ
    -0.09
    çĶľçĶľ
    -0.09
    åľ¨å¤ĸ
    -0.08
    称åij¼
    -0.08
    æ¡ħ
    -0.08
    èĩªæĿ¥
    -0.08
    POSITIVE LOGITS
    rück
    0.10
    oir
    0.09
    orman
    0.09
     Tribute
    0.09
    è±³
    0.08
     punct
    0.08
    YouTube
    0.08
    âľķ
    0.08
    Ĥ¬
    0.08
    ilon
    0.08
    Activations Density 0.021%

    No Known Activations