© 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. 49868
    Prev
    Next
    INDEX
    Explanations

    know 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
    ä¸įåŃĺåľ¨
    -0.09
    elm
    -0.08
    elson
    -0.08
     scept
    -0.07
     progress
    -0.07
    SEA
    -0.07
    æİ¥
    -0.07
    hl
    -0.07
    å¦į
    -0.07
    éªĩ
    -0.07
    POSITIVE LOGITS
    åıªçŁ¥éģĵ
    0.18
    æĢ»ä¹ĭ
    0.13
    æĪijä»¬çŁ¥éģĵ
    0.13
    åĢ¼å¾Ĺä¸ĢæıIJ
    0.12
    åijĬè¯īæĪij们
    0.11
    æĬĬæı¡
    0.10
    ä½Ĩå®ĥ
    0.10
    åijĬè¯īä½ł
    0.10
    æĪijçŁ¥éģĵ
    0.10
    å¾Īæ¸ħæ¥ļ
    0.10
    Activations Density 0.052%

    No Known Activations