© 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. 40311
    Prev
    Next
    INDEX
    Explanations

    findings and results

    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
    鲫
    -0.10
    æĥ³çĿĢ
    -0.10
    æĦļ
    -0.09
    ç»ıè¿ĩå¤ļå¹´
    -0.08
    fol
    -0.08
    anus
    -0.08
    رص
    -0.08
    å°±æĦıåij³çĿĢ
    -0.08
    Ãłng
    -0.08
    èµ·åºĬ
    -0.08
    POSITIVE LOGITS
    åıijçİ°
    0.11
    åıijçİ°éĹ®é¢ĺ
    0.11
    åıijçİ°äºĨ
    0.11
    çĻ¼çı¾
    0.10
    åijĬè¯īæĪij
    0.10
    .ud
    0.09
    صÙĦا
    0.09
    åıijæĺİ
    0.09
    产çĶŁ
    0.09
    rze
    0.09
    Activations Density 0.165%

    No Known Activations