© 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. 59196
    Prev
    Next
    INDEX
    Explanations

    piano

    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
    å·¾
    -0.11
    èĽŃ
    -0.11
    åı¯èĥ½åıijçĶŁ
    -0.10
    æ¤Ĵ
    -0.10
     caul
    -0.10
    enas
    -0.10
    æĸĭ
    -0.09
    èĹ¿
    -0.09
    èħĮ
    -0.09
    åĸĬ
    -0.09
    POSITIVE LOGITS
    éĴ¢çIJ´
    0.17
     piano
    0.17
     Piano
    0.16
     pian
    0.11
    éĶ®çĽĺ
    0.10
    empo
    0.10
    çħ¤çĤŃ
    0.09
    ðŁİ¹
    0.09
     coal
    0.09
    å¼¹
    0.09
    Activations Density 0.064%

    No Known Activations