© 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. 49373
    Prev
    Next
    INDEX
    Explanations

    read about or that

    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
    æĹ¥å¸¸å·¥ä½ľ
    -0.10
    è²Į
    -0.10
    ä¹ĭæīĢ
    -0.09
    OMPI
    -0.09
    аÑİÑĤ
    -0.09
     Ain
    -0.08
    ç»ĦåĽ¾
    -0.08
    anten
    -0.08
    .Priority
    -0.08
    羣çĪ±
    -0.08
    POSITIVE LOGITS
    æľī人说
    0.11
    äºĨ好å¤ļ
    0.10
    ä¸ĢäºĽ
    0.10
    æ³Ľ
    0.10
    ãĥĬãĤ¤
    0.10
    äºĨä¸ĢäºĽ
    0.10
    æĺİçĻ½äºĨ
    0.09
    äºĨ解åĪ°
    0.09
    æ´ŀ
    0.09
    lich
    0.09
    Activations Density 0.421%

    No Known Activations