© 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. 2140
    Prev
    Next
    INDEX
    Explanations

    quality issues or problems

    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
    æī¾åĪ°äºĨ
    -0.11
    æī¾åĪ°
    -0.10
    éĤ£ä»½
    -0.10
    ä¸ĢéĹª
    -0.10
    好æ¶Īæģ¯
    -0.09
    åĪłéĻ¤æĪIJåĬŁ
    -0.09
    æ¯Ļ
    -0.09
    è¹Ĵ
    -0.09
    ç¬ijçĿĢ
    -0.09
    èĢģçĪ·åŃIJ
    -0.09
    POSITIVE LOGITS
    ç«ŁçĦ¶
    0.10
    毫æĹł
    0.10
    ä¸į说
    0.10
    éĤĭ
    0.09
    ä¸ļæĢģ
    0.08
    æĺİãĤīãģĭ
    0.08
    æľįåĬ¡è´¨éĩı
    0.08
    çļĦæł¹æľ¬
    0.08
    严éĩįå½±åĵį
    0.08
    æł¹æľ¬ä¸į
    0.08
    Activations Density 0.051%

    No Known Activations