© 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. 40152
    Prev
    Next
    INDEX
    Explanations

    belief, trust, and confidence

    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
    éªĬ
    -0.09
    å¯Łçľĭ
    -0.08
    athom
    -0.08
    çĶ±æѤ
    -0.08
    æĢĿ绪
    -0.08
    马æĭī
    -0.08
    严èĤĥ
    -0.08
    WW
    -0.08
    _DEC
    -0.08
    æ½į
    -0.08
    POSITIVE LOGITS
    åı¦
    0.10
    æĭīæĸ¯
    0.10
    æ£į
    0.10
    ç³į
    0.09
    åĪ°æľŁ
    0.09
    åĬŀ好
    0.09
    æ°´æ³µ
    0.09
    éķĿ
    0.09
    解åĨ³éĹ®é¢ĺ
    0.09
    ubby
    0.09
    Activations Density 0.024%

    No Known Activations