© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7096
    Prev
    Next
    INDEX
    Explanations

    "bigger issue for many other users" and "more of this"

    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
    æĪijè¿ĺæĺ¯
    -0.10
    åIJ¦
    -0.09
    è¿ĺæĺ¯ä¼ļ
    -0.09
    åĬ¡
    -0.09
    åįłæį®äºĨ
    -0.08
    è´
    -0.08
    没éĶĻ
    -0.08
    æ´Ĺ礼
    -0.08
     ilma
    -0.08
    è¿ĺæĺ¯
    -0.08
    POSITIVE LOGITS
    æĹ©çĤ¹
    0.12
    ãĤĤãģ£ãģ¨
    0.12
    éĤ£ä¹Īå¤ļ
    0.11
    åĮ¡
    0.11
    éĤ£ä¹Ī容æĺĵ
    0.10
    èĢĮæĺ¯
    0.10
    åIJĮæł·çļĦ
    0.10
    åıįåĢĴ
    0.10
    åĵªæĢķæĺ¯
    0.09
     anymore
    0.09
    Activations Density 0.081%

    No Known Activations