© 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. 1709
    Prev
    Next
    INDEX
    Explanations

    locations followed by "in"

    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
    åı¤ä»Ĭ
    -0.10
     اÙĦداخÙĦ
    -0.10
    è¿Ľåİ»
    -0.10
    minster
    -0.09
    举缣
    -0.09
    ä¸Ĭç½ij
    -0.09
    ä½ıæĪ·
    -0.09
    åĿIJ
    -0.08
    è¿ĽæĿ¥
    -0.08
     Gaul
    -0.08
    POSITIVE LOGITS
    ä½įäºİ
    0.24
    ä½įæĸ¼
    0.17
    åľ¨åĮĹ京
    0.16
    åľ¨ä¸Ĭæµ·
    0.16
    åĪĨå¸ĥåľ¨
    0.16
    æīĢåľ¨åľ°
    0.16
    åľ¨æ·±åľ³
    0.15
    åĿIJèIJ½äºİ
    0.15
    éģįå¸ĥ
    0.14
     located
    0.14
    Activations Density 0.381%

    No Known Activations