© 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. 29622
    Prev
    Next
    INDEX
    Explanations

    signing names

    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
    è´¯
    -0.10
    å¿«æĬ¥
    -0.09
    赶ä¸Ĭ
    -0.09
    emme
    -0.08
    æľĢçĪ±
    -0.08
     Lopez
    -0.08
    je
    -0.08
     lore
    -0.08
     inters
    -0.08
    éĴ¢ç®¡
    -0.08
    POSITIVE LOGITS
    åĴ¦
    0.09
     payouts
    0.09
    åĭĩæ°Ķ
    0.09
    uffers
    0.09
    åľ¨éĩĮéĿ¢
    0.09
    çĸ«
    0.08
    è§īå¾Ĺå¾Ī
    0.08
    æ§IJ
    0.08
    转åŀĭ
    0.08
     outs
    0.08
    Activations Density 0.004%

    No Known Activations