© 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. 63504
    Prev
    Next
    INDEX
    Explanations

    time 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
    åĮĻ
    -0.11
    模èĮĥ
    -0.10
    éĴĵé±¼
    -0.09
    çĸı
    -0.09
    ithe
    -0.09
    æ¸ł
    -0.09
    æ£į
    -0.09
    æľĢåĪĿçļĦ
    -0.09
    éĴĵ
    -0.09
    éĩĩçŁ¿çŃī
    -0.09
    POSITIVE LOGITS
    è¶ĬæĿ¥è¶Ĭå°ij
    0.11
    ãģŀ
    0.11
    æľīéĻIJ
    0.09
    两个æľĪ
    0.09
    è¶ĬæĿ¥è¶Ĭ
    0.09
    éĶĻè¿ĩ
    0.08
     Madden
    0.08
    åī©
    0.08
    ç¿ĺ
    0.08
    ä¸įå¤ļ
    0.08
    Activations Density 0.022%

    No Known Activations