© 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. 48979
    Prev
    Next
    INDEX
    Explanations

    academic conferences and journals

    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
    ÑĩÑĥ
    -0.11
    æ²īéĩį
    -0.09
     Marble
    -0.09
     whip
    -0.08
     Ree
    -0.08
    ä½į
    -0.08
    é¬Ī
    -0.08
     ruling
    -0.08
    æĿĢ人
    -0.08
    æĺ¯æĪijåĽ½
    -0.08
    POSITIVE LOGITS
    人士
    0.09
    æľŁåĪĬ
    0.09
    èijĹä½ľ
    0.09
    enance
    0.09
    对æѤ
    0.08
    ugg
    0.08
    æĸĩç«ł
    0.08
    åŃ¦æľ¯
    0.08
    ordial
    0.08
    ç»ıéĶĢ
    0.08
    Activations Density 0.025%

    No Known Activations