© 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. 34830
    Prev
    Next
    INDEX
    Explanations

    career high school highest

    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
    寥
    -0.13
    äºı
    -0.11
    ä¸Ģç»ı
    -0.10
    èĢģ人家
    -0.09
    éķ¶
    -0.09
    æijĩ
    -0.09
    ä¸īä½įä¸Ģä½ĵ
    -0.09
    ÑģÑĤал
    -0.09
    å°ıäºĭ
    -0.09
    çļĦ羣å®ŀæĢ§
    -0.09
    POSITIVE LOGITS
    åŃļ
    0.09
    æľĢ大
    0.09
    çī©ä»·
    0.09
    庶
    0.09
    ìĸ´ìĦľ
    0.08
    åĽ½åĨħå¤ĸ
    0.08
    çļĦæľĢ大
    0.08
    ritch
    0.08
     Illegal
    0.08
     Wade
    0.08
    Activations Density 0.019%

    No Known Activations