© 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. 39406
    Prev
    Next
    INDEX
    Explanations

    question or list items

    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
    çļĦèĥĮåIJİ
    -0.10
    æijŀ
    -0.10
    æĮ½
    -0.09
    ä¸ī家
    -0.09
    ä¸īæĺ¯
    -0.09
    å£ħ
    -0.09
    å¨ĥå¨ĥ
    -0.09
    èĻ½çĦ¶æĺ¯
    -0.09
    åįĹè·¯
    -0.09
    ital
    -0.09
    POSITIVE LOGITS
    odic
    0.12
    åĬ¿
    0.10
    çī¹åĪ«æĺ¯
    0.09
    ilon
    0.09
    çļĦ人æĿ¥è¯´
    0.09
    è¾°
    0.08
    æĪĸèĢħæĺ¯
    0.08
    ensitive
    0.08
    åºĶåıĬæŶ
    0.08
    è°Ħ
    0.08
    Activations Density 0.131%

    No Known Activations