© 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. 31667
    Prev
    Next
    INDEX
    Explanations

    for + duration

    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
    éĿ¢ç§¯çº¦
    -0.10
    åįģå¤ļå¹´
    -0.10
    两天
    -0.10
    èĤĵ
    -0.09
    æĢ»éĿ¢ç§¯
    -0.09
    éĵ³
    -0.09
    åĩłåįģå¹´
    -0.09
    ific
    -0.09
    velt
    -0.08
    åįģä½Ļå¹´
    -0.08
    POSITIVE LOGITS
    足以
    0.10
    æī§æ³ķ
    0.09
     cop
    0.09
    coc
    0.09
    ç«
    0.09
    åĵªæĢķæĺ¯
    0.09
    éĻIJ度
    0.09
    ç´łè´¨
    0.08
    Hor
    0.08
    åĨľå®¶ä¹IJ
    0.08
    Activations Density 0.184%

    No Known Activations