© 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. 47516
    Prev
    Next
    INDEX
    Explanations

    strip supremacy / nitrous oxide / Summit paint / flow testing / Unlimited Class / survivor class

    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
    jni
    -0.09
    æµij
    -0.09
    èĪĨæĥħ
    -0.09
    åıijçİ°èĩªå·±
    -0.08
    ogne
    -0.08
    nero
    -0.08
    çĶŁäº§è®¾å¤ĩ
    -0.08
    æĿ¯åŃIJ
    -0.08
    交åıī
    -0.08
    airy
    -0.08
    POSITIVE LOGITS
    WithError
    0.09
    ÑģÑĤан
    0.08
    缮çļĦåľ¨äºİ
    0.08
    ë²Į
    0.08
    ä¸Ģ代
    0.08
    æľ¬çĿĢ
    0.08
    ética
    0.08
    UV
    0.08
    er
    0.08
    èĥ½åģļåĪ°
    0.08
    Activations Density 0.018%

    No Known Activations