© 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. 49280
    Prev
    Next
    INDEX
    Explanations

    first ever, first career, first history

    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
    äºĨæĪijçļĦ
    -0.10
    çļĦéģĵçIJĨ
    -0.09
    éĻĦè¿ij
    -0.09
    Days
    -0.09
    ä¹ŁçŁ¥éģĵ
    -0.09
     Nearby
    -0.09
    nes
    -0.09
    ấn
    -0.09
     {?}
    -0.09
    æ³»
    -0.09
    POSITIVE LOGITS
    è¿ĩç¨ĭå½ĵä¸Ń
    0.09
    åĩºçİ°
    0.08
     rall
    0.08
    羣æŃ£
    0.08
    æŃ£è§Ħ
    0.07
    宵
    0.07
     truly
    0.07
    isha
    0.07
    æĵħ
    0.07
    åı¤éķĩ
    0.07
    Activations Density 0.020%

    No Known Activations