© 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. 17927
    Prev
    Next
    INDEX
    Explanations

    before something else

    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
    åĽŀäºĭ
    -0.09
    ä»»ä½ķæŶåĢĻ
    -0.09
    iston
    -0.09
    izo
    -0.09
    âĪİ
    -0.08
    è¶ĬæĿ¥è¶Ĭå°ij
    -0.08
     دائÙħا
    -0.08
    åİĨæĿ¥
    -0.08
    æĿ¥åĽŀ
    -0.08
    ihu
    -0.08
    POSITIVE LOGITS
    çłŃ
    0.09
    åĨħåľ¨
    0.09
    è¢Ĥ
    0.09
     ÙĪبعد
    0.09
    WARDS
    0.08
    åIJĦèĩªçļĦ
    0.08
    äºĨ解ä¸Ģä¸ĭ
    0.08
    åĽ½ãģ®
    0.08
    åŁºæķ°
    0.08
    wards
    0.08
    Activations Density 0.027%

    No Known Activations