© 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. 62139
    Prev
    Next
    INDEX
    Explanations

    time trials, choice, gameplay, level cap

    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
    å½±è§Ĩåī§
    -0.09
    æī§
    -0.09
    ä¸Ģå¹ķ
    -0.08
    ç»Ļä½łä»¬
    -0.08
    è¦ģçĶ¨
    -0.08
    è°Ī
    -0.08
    åĭŁ
    -0.08
    æ¯Ĥ
    -0.08
    çķĮ第ä¸Ģ
    -0.08
    樵
    -0.08
    POSITIVE LOGITS
    辨
    0.10
     Pron
    0.09
     Append
    0.09
    æ¸IJ
    0.09
    éĩįå¤į
    0.09
     calendar
    0.09
     mutil
    0.09
    bang
    0.09
     append
    0.09
     tong
    0.08
    Activations Density 0.171%

    No Known Activations