© 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. 24109
    Prev
    Next
    INDEX
    Explanations

    calculus and derivatives

    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
    Untitled
    -0.09
    fixture
    -0.08
    ORMAL
    -0.08
    设æĸ½
    -0.08
    èIJ
    -0.08
    èµĦè´¨
    -0.08
    å¡
    -0.08
     Berger
    -0.08
     semen
    -0.08
    athing
    -0.08
    POSITIVE LOGITS
    æİī
    0.10
    æĶ¾å¿ĥ
    0.09
    ç¨į
    0.09
    elman
    0.09
    çĺģ
    0.09
    åĪĨæĶ¯
    0.08
    é«ĺçŃīéĻ¢æł¡
    0.08
     ÙĨÙĩا
    0.08
    nants
    0.08
    IDES
    0.08
    Activations Density 0.153%

    No Known Activations