© 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. 30681
    Prev
    Next
    INDEX
    Explanations

    science journal articles

    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
    å±ij
    -0.09
    ä½ļ
    -0.09
    opc
    -0.08
    ç«Ļéķ¿
    -0.08
    æ·¦
    -0.08
    å¼Ģæľº
    -0.08
    å¼ĢåıijåĮº
    -0.08
    客è¿IJ
    -0.08
    ä¿Ŀç¨İ
    -0.08
    åIJĦåİ¿
    -0.08
    POSITIVE LOGITS
    æĶ¾æīĭ
    0.11
    审
    0.10
    science
    0.10
    ç§ijåѦ
    0.10
    è
    0.09
     pylab
    0.09
     reviewers
    0.09
    Science
    0.09
    æľŁåĪĬ
    0.09
    è¿°
    0.09
    Activations Density 0.171%

    No Known Activations