© 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. 18214
    Prev
    Next
    INDEX
    Explanations

    will a future event

    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
    ä¸įä¹ħ
    -0.13
    åİĨæĿ¥
    -0.11
    马ä¸Ĭå°±
    -0.11
    éķ¿æľŁä»¥æĿ¥
    -0.11
    ä¸Ģå¼Ģå§ĭ
    -0.11
    ä¸ĢèĪ¬
    -0.10
    æŃ¤æ¬¡
    -0.10
    æľīæŶ
    -0.10
    ä¸Ģå¼Ģå§ĭå°±
    -0.10
    è¿ijæĹ¥
    -0.09
    POSITIVE LOGITS
    기ê°Ģ
    0.09
    åħ¬å¼Ģ课
    0.09
    诰
    0.09
    è°²
    0.09
    å®ī举
    0.09
    溺
    0.09
    å°¤åħ¶æĺ¯åľ¨
    0.08
    幡
    0.08
    æĪ¾
    0.08
    agra
    0.08
    Activations Density 0.069%

    No Known Activations