© 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. 47685
    Prev
    Next
    INDEX
    Explanations

    setting a high standard

    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
    Not in Any Lists

    No Comments

    Negative Logits
    åīŀ
    -0.09
    (solution
    -0.09
     choÄĩ
    -0.09
    дол
    -0.08
    ccione
    -0.08
    _ta
    -0.08
    ìĪľ
    -0.08
    欤
    -0.08
    sein
    -0.08
     обÑĢаÑī
    -0.08
    POSITIVE LOGITS
    æĹłæīĢ
    0.11
    éģĹ产
    0.10
    æŀģé«ĺ
    0.09
    å¾Īé«ĺ
    0.09
    èijij
    0.09
    æĩĤäºĭ
    0.09
    ä¸įæĸŃæıIJé«ĺ
    0.09
    å¾Īé«ĺçļĦ
    0.09
    éģĹ
    0.09
    ç«ĻçĿĢ
    0.09
    Activations Density 0.035%

    No Known Activations