© 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. 35828
    Prev
    Next
    INDEX
    Explanations

    preparing what, wait for, tried again

    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
    æ·ĭ
    -0.09
    åįĩ
    -0.09
    éĢłç¦ı
    -0.08
    ç½°
    -0.08
    çĪĨ
    -0.08
     teaches
    -0.08
    è¿IJèIJ¥ç®¡çIJĨ
    -0.08
    .CreateInstance
    -0.08
     taught
    -0.08
    Recovered
    -0.08
    POSITIVE LOGITS
    追éĢIJ
    0.10
    è¯ķæİ¢
    0.10
    çŃĽéĢī
    0.10
    ç«ŀäºī
    0.09
    ä¿Ŀå¯Ĩ
    0.09
    åı£å¾Ħ
    0.09
    æĬ¥ä»·
    0.09
    çŃ¾çº¦
    0.09
    èģĶç³»
    0.09
    æīĵåIJ¬
    0.09
    Activations Density 0.076%

    No Known Activations