© 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. 22959
    Prev
    Next
    INDEX
    Explanations

    between, on, by, from, at

    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
    åħļçļĦ建设
    -0.08
    ë´ĩ
    -0.08
     Ñĩа
    -0.08
    ç¬ı
    -0.08
    BUY
    -0.08
    为äºĨæĽ´å¥½
    -0.08
     Sisters
    -0.08
    ofire
    -0.08
    è¯ľ
    -0.08
    æīĵæŀ¶
    -0.08
    POSITIVE LOGITS
    åľ¨ä»Ĭå¹´
    0.20
    è¿ijæĹ¥
    0.15
     during
    0.15
    è¿ijæľŁ
    0.15
    æĹ©åľ¨
    0.15
    åݻ年
    0.14
    æĹ¥åīį
    0.14
    并äºİ
    0.14
     recently
    0.13
    äºİ
    0.13
    Activations Density 0.606%

    No Known Activations