© 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. 2241
    Prev
    Next
    INDEX
    Explanations

    by the end of clauses

    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
    åĨį说
    -0.08
    æ´»çĿĢ
    -0.08
    ont
    -0.08
     Gad
    -0.07
    说起
    -0.07
    äºĨè§£æĽ´å¤ļ
    -0.07
     Cop
    -0.07
     Bid
    -0.07
    ol
    -0.07
    ä½İä¸ĭ
    -0.07
    POSITIVE LOGITS
     бÑĥм
    0.10
    CELER
    0.10
    AINER
    0.09
    åı¯ä»¥è¯´æĺ¯
    0.09
    á»Ĵ
    0.09
    ãĥ¬ãĤ¤
    0.09
    æĹ¢èĥ½
    0.09
    cente
    0.08
    obox
    0.08
    _FILL
    0.08
    Activations Density 0.595%

    No Known Activations