© 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. 1963
    Prev
    Next
    INDEX
    Explanations

    band name

    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
    è¿Ļä½į
    -0.11
    ä¸Ģç¯ĩ
    -0.11
    ä¸Ģ座
    -0.11
     Tage
    -0.10
    è¿ĻåIJį
    -0.09
    ä¸Ģçīĩ
    -0.09
    ITCH
    -0.09
    warf
    -0.09
    ä¸ĢåĪ»
    -0.09
    è¿Ļç¯ĩ
    -0.09
    POSITIVE LOGITS
    æĪIJç«ĭ
    0.09
    å½ĵåľ°çļĦ
    0.09
    åIJİå¤ĩ
    0.09
    çī¹æ®ĬçļĦ
    0.09
    æľĢå¿«
    0.08
    ники
    0.08
    羡
    0.08
     обÑĥÑĩ
    0.08
    æĪIJç«ĭäºĨ
    0.08
     trou
    0.08
    Activations Density 0.147%

    No Known Activations