© 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. 30173
    Prev
    Next
    INDEX
    Explanations

    oldest

    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
    æĻļå¹´
    -0.10
    ç²¾èĭ±
    -0.10
    åIJĦ个æĸ¹éĿ¢
    -0.10
    鼷
    -0.09
    upe
    -0.09
     неÑģколÑĮкиÑħ
    -0.09
    transition
    -0.09
    éĿĴå¹´
    -0.08
     leap
    -0.08
    é¢ĸ
    -0.08
    POSITIVE LOGITS
    åı¤èĢģ
    0.13
    æĤłä¹ħ
    0.12
     oldest
    0.12
    æĹ©åľ¨
    0.10
    åı¤èĢģçļĦ
    0.10
    æľĢæĹ©çļĦ
    0.10
     lâu
    0.10
    æĪIJç«ĭäºİ
    0.10
    æĮģä¹ħ
    0.09
    çļĦèĢģ
    0.09
    Activations Density 0.039%

    No Known Activations