© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 17725
    Prev
    Next
    INDEX
    Explanations

    No, Yes, or Nope

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸ĢåŃĹ
    -0.09
    天河
    -0.08
    è¿Ļæł·åģļ
    -0.08
    è¿ĺ好
    -0.08
     Pron
    -0.08
    mark
    -0.08
    ä¸ĢèĪ¬çļĦ
    -0.07
    artin
    -0.07
    çĿĢæīĭ
    -0.07
    &q
    -0.07
    POSITIVE LOGITS
    ç´¯äºĨ
    0.09
    éĻĽä¸ĭ
    0.09
    æľ¬ç½ij
    0.09
    ç½ķ
    0.09
    ANC
    0.09
    é«¡
    0.09
    赦
    0.09
    å¯ĤéĿĻ
    0.09
    å®Ŀè´µ
    0.09
    é¤IJ
    0.08
    Activations Density 0.048%

    No Known Activations