© 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. 57897
    Prev
    Next
    INDEX
    Explanations

    shrieks of delight

    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
    è·ŁæĪij说
    -0.10
    åĽ½å®ī
    -0.10
    æĹ©æĻļ
    -0.09
    å¸¦ä½ł
    -0.09
    好åIJĹ
    -0.09
    æ·±å¤ľ
    -0.09
    éĢģåĪ°
    -0.09
    让èĩªå·±
    -0.09
    åijķ
    -0.09
    æĻļå¹´
    -0.09
    POSITIVE LOGITS
    纷纷
    0.11
    æİĮ声
    0.11
    åĩłåIJį
    0.10
    欢åij¼
    0.10
    纷纷表示
    0.10
    åħ¨åľº
    0.10
    åĵį
    0.09
    éļıä¹ĭ
    0.09
    äºī缸
    0.09
    åIJĦèĩª
    0.09
    Activations Density 0.023%

    No Known Activations