© 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. 53520
    Prev
    Next
    INDEX
    Explanations

    starts with "apparently"

    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
    èĤ¯å®ļ
    -0.11
    ä¸į失
    -0.10
    æķŀå¼Ģ
    -0.10
    表éĿ¢ä¸Ĭ
    -0.09
    æĥ³å¿ħ
    -0.09
    éĥ¾
    -0.09
    åIJĨ
    -0.09
    erval
    -0.09
    æģIJæĢķ
    -0.09
    æĺ¯åIJ¦ä¼ļ
    -0.08
    POSITIVE LOGITS
     även
    0.09
    好人
    0.09
    ãĤĤãģªãģı
    0.09
    æĺ¯è¦ģ
    0.08
    ãģĵãĤĮãģĮ
    0.08
    AIM
    0.08
    ULD
    0.08
    ä¸į管
    0.08
    è¿ľ
    0.08
    ikon
    0.08
    Activations Density 0.022%

    No Known Activations