© 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. 59357
    Prev
    Next
    INDEX
    Explanations

    report conclusions and recommendations

    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
     upcoming
    -0.08
     ÑĢаÑģпÑĢ
    -0.08
     hè
    -0.08
    é¢Ĩè·ij
    -0.08
    iasi
    -0.08
    пÑĢовод
    -0.08
    éľİ
    -0.07
    çĶ³æĬ¥
    -0.07
     jd
    -0.07
    RS
    -0.07
    POSITIVE LOGITS
    ç»ĵ论
    0.16
    æĬ¥åijĬ
    0.12
     conclusions
    0.12
     findings
    0.12
     recommendations
    0.11
    审议
    0.11
     conclusion
    0.10
    åł±åijĬ
    0.10
     Recommendations
    0.10
     recommending
    0.10
    Activations Density 0.071%

    No Known Activations