© 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. 35157
    Prev
    Next
    INDEX
    Explanations

    biological taxonomy

    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
     dra
    -0.09
    á»į
    -0.09
     Loch
    -0.09
     chù
    -0.08
    éĻIJæľŁ
    -0.08
    å¤ĸç±į
    -0.08
     Sage
    -0.08
    主管éĥ¨éŨ
    -0.08
    äºĨä¸Ģåľº
    -0.08
    éĴ§
    -0.08
    POSITIVE LOGITS
    éra
    0.10
    é©·
    0.09
    è¾Ĥ
    0.09
    zek
    0.09
    ä¸įä¸Ĭ
    0.09
    ĻĤ
    0.09
    opsis
    0.09
    spl
    0.09
    çĶŁæ´»çļĦ
    0.09
    å¯Ŀ
    0.08
    Activations Density 0.218%

    No Known Activations