© 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. 22761
    Prev
    Next
    INDEX
    Explanations

    do not use

    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
    agnostics
    -0.10
    æľªç»ı
    -0.09
    ç«Ł
    -0.09
    ä¸Ģ缴
    -0.08
     BOTH
    -0.08
     somehow
    -0.08
    èµ°ä¸Ĭ
    -0.08
    æĢĢçĸij
    -0.08
    EM
    -0.08
    ç«Łæĺ¯
    -0.08
    POSITIVE LOGITS
    åı¦è¡Į
    0.18
    åı¦æľī
    0.15
    åı¦å¤ĸ
    0.13
    åı¦
    0.12
     elsewhere
    0.12
    åı¦ä¸Ģè¾¹
    0.11
    åįķçĭ¬
    0.11
    ä¸ĵéŨ
    0.11
    åı¦å¤ĸä¸Ģ个
    0.10
    æĽ´éĢĤåIJĪ
    0.10
    Activations Density 0.137%

    No Known Activations