© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38516
    Prev
    Next
    INDEX
    Explanations

    what remains or is left

    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
    èĩªèº«çļĦ
    -0.09
    åĮ£
    -0.09
    è¾¾ä¸įåĪ°
    -0.09
    æĮģæľīçļĦ
    -0.09
    éĺ¿éĩĮå·´å·´
    -0.08
    é£Łæ¬²
    -0.08
    æīĢåľ¨çļĦ
    -0.08
    æģķ
    -0.08
    ysics
    -0.08
    讳
    -0.08
    POSITIVE LOGITS
    åī©ä¸ĭ
    0.33
    åī©
    0.31
    åī©ä¸ĭçļĦ
    0.31
     remaining
    0.29
    åī©ä½Ļ
    0.28
    remaining
    0.25
     Remaining
    0.24
    Remaining
    0.24
    åıªåī©
    0.22
    .remaining
    0.22
    Activations Density 0.044%

    No Known Activations