© 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. 54779
    Prev
    Next
    INDEX
    Explanations

    what do you do?

    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
     ??
    -0.11
     ???
    -0.10
     either
    -0.10
     (?)
    -0.10
     (?
    -0.10
    (?
    -0.10
    ??
    -0.09
     ?????
    -0.09
    并ä¸įæĺ¯
    -0.08
     ?
    -0.08
    POSITIVE LOGITS
    ØŁ
    0.12
     denn
    0.12
    Õŀ
    0.11
    еÑģÑĤв
    0.10
    åĢ¼å¾Ĺåħ³æ³¨
    0.10
    оÑĢа
    0.10
    æijħ
    0.09
    ï¼Ł↵↵
    0.09
    _unknown
    0.09
    ï¼Ł↵
    0.09
    Activations Density 0.180%

    No Known Activations