© 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. 61466
    Prev
    Next
    INDEX
    Explanations

    guest access

    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
    åĿļæĮģä¸įæĩĪ
    -0.09
    åı¥è¯Ŀ
    -0.09
    osed
    -0.09
    ä¸Ģ声
    -0.09
    侧éĿ¢
    -0.09
    积æŀģå¼Ģå±ķ
    -0.09
    æģŃåĸľ
    -0.09
    å¥¥åľ°åĪ©
    -0.09
    ç½ij讯
    -0.08
    好好
    -0.08
    POSITIVE LOGITS
     anon
    0.11
    anonymous
    0.11
     guest
    0.11
     Anonymous
    0.10
     anonymously
    0.10
     anonymous
    0.10
    guest
    0.10
    身份
    0.10
    Guest
    0.10
    游客
    0.09
    Activations Density 0.033%

    No Known Activations