© 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. 3194
    Prev
    Next
    INDEX
    Explanations

    organizational structure and defined terms

    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
    nik
    -0.09
    å»ī
    -0.09
    è®°èĢħ
    -0.08
    éģŃ
    -0.08
    å°ij
    -0.08
    æľĢå°ij
    -0.08
    ä»İåīį
    -0.08
    breaker
    -0.07
    éĢIJ
    -0.07
    æĶ¯
    -0.07
    POSITIVE LOGITS
    wil
    0.09
    çİĸ
    0.09
    ç»ıèIJ¥æ´»åĬ¨
    0.09
    æĤ¨åIJĮæĦı
    0.09
    æ³Ħ
    0.09
    æĹłæĦı
    0.09
    éĥijéĩį
    0.09
    å´ĩ
    0.09
    .null
    0.09
    天èĬ±
    0.08
    Activations Density 0.034%

    No Known Activations