© 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. 28103
    Prev
    Next
    INDEX
    Explanations

    received or obtained by

    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
    lete
    -0.10
    åıªè¦ģæľī
    -0.09
    èĦ¯
    -0.09
    ç´łè´¨
    -0.09
    æѧè§Ĩ
    -0.09
    æľĢéĩįè¦ģçļĦ
    -0.08
     Stef
    -0.08
    æľĢåħ³éĶ®çļĦ
    -0.08
    agine
    -0.08
    交æİ¥
    -0.08
    POSITIVE LOGITS
    åĩºæĿ¥çļĦ
    0.17
    æĿ¥çļĦ
    0.15
    å½¢æĪIJçļĦ
    0.14
    æĿ¥èĩªäºİ
    0.14
    æĿ¥èĩª
    0.14
    åĩºèĩª
    0.14
    มาà¸Īาà¸ģ
    0.13
    æĿ¥æºIJäºİ
    0.13
    æıIJä¾ĽçļĦ
    0.12
    ä½ľãģ£ãģŁ
    0.12
    Activations Density 0.325%

    No Known Activations