© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9733
    Prev
    Next
    INDEX
    Explanations

    practices, tactics, strategies

    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
    æĸĩçī©ä¿ĿæĬ¤
    -0.11
    æ°ijçĶ¨
    -0.09
    ä¸ĩä¸Ģ
    -0.09
    æľīæĦıæĢĿ
    -0.09
    artifact
    -0.09
    ç»ıå¼Ģ
    -0.09
    å°±ä¸ļå²Ĺä½į
    -0.09
    åıijå±ķçIJĨ念
    -0.08
    çĶŁäº§çĶŁæ´»
    -0.08
    æľī趣
    -0.08
    POSITIVE LOGITS
    çŃĸçķ¥
    0.13
    èĮĥåĨ°
    0.10
     tactics
    0.10
    èIJ¥éĶĢ
    0.10
    æĪĺæľ¯
    0.09
     strategies
    0.09
    æĭĽ
    0.09
    _strategy
    0.09
    çĭĻ
    0.09
     Tactics
    0.09
    Activations Density 0.143%

    No Known Activations