© 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. 862
    Prev
    Next
    INDEX
    Explanations

    lists of things

    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·ĭ
    -0.10
    说æĪij
    -0.09
    çªĿ
    -0.09
    礼仪
    -0.09
    ç´ł
    -0.09
     Farr
    -0.09
    quet
    -0.09
    åĶĩ
    -0.09
     воп
    -0.09
     covered
    -0.08
    POSITIVE LOGITS
    è¯įè¯Ń
    0.11
    å°±è¿ij
    0.10
    åı¥
    0.10
    dens
    0.10
    éĵ¿
    0.09
    è¾ŀ
    0.09
    è¯į
    0.09
    好å¤Ħ
    0.09
    ä»Ħ
    0.09
    çĤ¼
    0.09
    Activations Density 0.053%

    No Known Activations