© 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. 32380
    Prev
    Next
    INDEX
    Explanations

    supporters of

    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
    ä¸ĢåįĬ
    -0.10
    åĴİ
    -0.09
    æĽ´å¤ļ精彩
    -0.09
     resisting
    -0.09
    äºĨ解ä¸Ģä¸ĭ
    -0.09
    hound
    -0.09
    é«ĺå³°æľŁ
    -0.09
    建档
    -0.08
    æĹ¥æĬ¥è®°èĢħ
    -0.08
    inate
    -0.08
    POSITIVE LOGITS
    é¢Ĩè¢ĸ
    0.09
    ä»İèĢĮ使
    0.09
    ä¸¤åľ°
    0.09
    rsa
    0.09
    etsk
    0.08
     tack
    0.08
    ëł¹
    0.08
    ниÑĨа
    0.08
    lient
    0.08
    AIT
    0.08
    Activations Density 0.024%

    No Known Activations