© 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. 58498
    Prev
    Next
    INDEX
    Explanations

    denied, affirmed, appellant

    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
    ä¸įåĥı
    -0.09
    æīįæľī
    -0.08
    å¼ĢåĬŀ
    -0.08
    è¿ĽæĿ¥
    -0.08
    plier
    -0.08
     supposedly
    -0.08
    好åĩłä¸ª
    -0.08
    åĬŀ
    -0.07
    lier
    -0.07
    è·ŁæĪij说
    -0.07
    POSITIVE LOGITS
     hereby
    0.11
    å½ĵä¹ĭæĹłæĦ§
    0.10
    äºĪ以
    0.10
    .setResult
    0.10
    æݨèįIJ
    0.09
     recommand
    0.09
    ãģĬãģĻãģĻ
    0.09
    æľ¬æľŁ
    0.09
    éĥ¨åĪĨåĨħ容
    0.09
    建议
    0.09
    Activations Density 0.122%

    No Known Activations