© 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. 33901
    Prev
    Next
    INDEX
    Explanations

    from what I

    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
    æģ¼
    -0.09
    å°ģ
    -0.09
    .Marshal
    -0.09
     trope
    -0.08
    æıIJ款
    -0.08
    å¹Ķ
    -0.08
    æľīåħ´è¶£
    -0.08
    à¹Ħà¸ķ
    -0.08
    æıIJ
    -0.08
    说å®ŀè¯Ŀ
    -0.08
    POSITIVE LOGITS
    è°ĥæŁ¥æĺ¾ç¤º
    0.11
    æĥħåĨµæĿ¥çľĭ
    0.10
    è¿Ļ两年
    0.10
    åĪĿæŃ¥
    0.09
    æĬ¥ä¸ļ
    0.09
    æĿ¥çľĭ
    0.09
    åĬłä¹ĭ
    0.09
    èķĻ
    0.09
    cket
    0.09
    è¿Ļåĩłä¸ª
    0.09
    Activations Density 0.225%

    No Known Activations