© 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. 4648
    Prev
    Next
    INDEX
    Explanations

    winning streaks

    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
    yc
    -0.10
    dk
    -0.08
    çļĦ身ä½ĵ
    -0.08
    ä¸į满
    -0.08
     myfile
    -0.08
    ç²¾éĢļ
    -0.08
    ds
    -0.08
    è´¯
    -0.08
    贯穿
    -0.08
    ç³»åĪĹæ´»åĬ¨
    -0.08
    POSITIVE LOGITS
    обÑīа
    0.10
    MESS
    0.10
    廳
    0.09
     ÑģкаÑĩаÑĤÑĮ
    0.09
    ç¼Ĩ
    0.08
    ä¸ĢéĹª
    0.08
    ialis
    0.08
    ingham
    0.08
    åĵĨ
    0.08
    ä¿Ĺ
    0.08
    Activations Density 0.021%

    No Known Activations