© 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. 1668
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation

    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
    çļĦä¸ĢåĪĩ
    -0.10
    èºģ
    -0.10
    好æĦŁ
    -0.10
     Klo
    -0.09
    aded
    -0.09
     зани
    -0.09
    kee
    -0.09
    AMY
    -0.09
    京éĥ½
    -0.09
    å¹´ä¹ĭ
    -0.09
    POSITIVE LOGITS
    å°¤åħ¶æĺ¯åľ¨
    0.08
    åİŁæĿ¥æĺ¯
    0.08
    åħ¼
    0.08
    åĨ³ä¸į
    0.08
    çī¹åĪ«æĺ¯åľ¨
    0.08
    æĢĢçĿĢ
    0.08
    åĴĮæĬĢæľ¯
    0.07
    éĥ½è¯´
    0.07
    åħ¼åħ·
    0.07
    å°¤åħ¶
    0.07
    Activations Density 0.406%

    No Known Activations