© 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. 31824
    Prev
    Next
    INDEX
    Explanations

    an excuse to

    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
    èĩªæĿ¥
    -0.11
    æ¿Ĵ
    -0.10
    缴è¾ĸ
    -0.10
     ÙħÙĨت
    -0.10
    ä½Ĩæĺ¯æĪij
    -0.10
     конеÑĩно
    -0.10
     اÙĦتاب
    -0.10
    ç¡®å®ŀ
    -0.09
    ä¸ĵåľº
    -0.09
    åģļæ³ķ
    -0.09
    POSITIVE LOGITS
    åıĪä¸Ģ次
    0.10
    çīµ
    0.09
     excuses
    0.08
     excuse
    0.08
    ends
    0.08
    ılı
    0.08
    çīµå¼ķ
    0.08
    åıĪè¦ģ
    0.08
    触
    0.07
    éĵĭ
    0.07
    Activations Density 0.110%

    No Known Activations