© 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. 59434
    Prev
    Next
    INDEX
    Explanations

    first derivative of

    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
    Debugger
    -0.09
    .hd
    -0.09
    å®ĺ
    -0.08
    _beam
    -0.08
    воÑĢ
    -0.08
    umb
    -0.08
    åĨħå¿ĥ
    -0.08
    HEME
    -0.08
    åıĹçģ¾
    -0.08
    boat
    -0.08
    POSITIVE LOGITS
    kaar
    0.10
     pena
    0.09
    ariat
    0.09
    åĨ¢
    0.09
    å°ıä¼Ļ伴们
    0.09
    åĴ«
    0.08
    обÑĢ
    0.08
    å¢ŀ强äºĨ
    0.08
    ijken
    0.08
    ç»´
    0.08
    Activations Density 0.002%

    No Known Activations