© 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. 34971
    Prev
    Next
    INDEX
    Explanations

    coming on as a substitute

    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¸įè¿ľ
    -0.12
    å½ĵä¹ĭæĹłæĦ§
    -0.11
    éĢIJå¹´
    -0.10
    å¿łå®ŀ
    -0.10
    åĿ¨
    -0.10
    éĺĥ
    -0.09
    缺å¸Ń
    -0.09
    榫
    -0.09
    ä¸Ģ件
    -0.09
    离ä¸įå¼Ģ
    -0.09
    POSITIVE LOGITS
    als
    0.09
    оÑī
    0.08
     Hib
    0.08
    True
    0.08
    ady
    0.08
    è¿ĽæĿ¥
    0.07
    oni
    0.07
    æĽ´æľī
    0.07
    ä»£æĽ¿
    0.07
    樵
    0.07
    Activations Density 0.017%

    No Known Activations