© 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. 2144
    Prev
    Next
    INDEX
    Explanations

    kind of or sort 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
    èİ«
    -0.12
    åĪ«è¯´
    -0.11
     Vict
    -0.10
    æł·å¼ı
    -0.10
    两类
    -0.09
    æĸ¹è¨Ģ
    -0.09
    æĭħå½ĵ
    -0.09
    éłĺ
    -0.09
    æľīåĪ©
    -0.09
    ä¹Łå¥½
    -0.09
    POSITIVE LOGITS
    æ¡ħ
    0.10
    trag
    0.08
    欢è¿İæĤ¨
    0.08
    utto
    0.08
    æĥħåĨµä¸ĭ
    0.08
    èµĦæºIJæķ´åIJĪ
    0.08
    çŁŃæľŁ
    0.08
    éķ¿æľŁ
    0.08
    olk
    0.08
    ëĮĢë¡ľ
    0.08
    Activations Density 0.009%

    No Known Activations