© 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. 62169
    Prev
    Next
    INDEX
    Explanations

    passed the ball

    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
    éľĩ
    -0.10
    æĹłæĥħ
    -0.09
    åIJĦè¡ĮåIJĦä¸ļ
    -0.09
    èĬŁ
    -0.09
    é£İæł¼
    -0.09
    æīĥ
    -0.09
    Ĩµ
    -0.09
    æ³ģ
    -0.09
    æłĩéħį
    -0.09
    ç»Ļä½łä»¬
    -0.09
    POSITIVE LOGITS
    ç«Ļéķ¿
    0.09
    课æĸĩ
    0.08
     пеÑĢевод
    0.07
    ãİĿ
    0.07
    azaar
    0.07
    ags
    0.07
    çķ¶æĻĤ
    0.07
    å½ĵæŶ
    0.07
    -generated
    0.07
     direct
    0.07
    Activations Density 0.025%

    No Known Activations