© 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. 62345
    Prev
    Next
    INDEX
    Explanations

    non-exclusive license

    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
    被åĪ¤
    -0.11
    绿èī²éĢļéģĵ
    -0.09
     unprotected
    -0.09
    è¿IJæ²³
    -0.08
    èĻ±
    -0.08
    ѳ
    -0.08
    ãĤ¯ãĥŃ
    -0.08
    çĿĢä»ĸ
    -0.08
    åºIJ
    -0.08
    gef
    -0.08
    POSITIVE LOGITS
    人家
    0.09
    åĶ®
    0.09
    ç»ĦåĽ¢
    0.08
     Yaz
    0.08
    大大å°ı
    0.08
     пеÑĩ
    0.08
    ä¸įè¿ĩæĺ¯
    0.08
    ç±į
    0.08
    integr
    0.08
     Fro
    0.08
    Activations Density 0.143%

    No Known Activations