© 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. 56343
    Prev
    Next
    INDEX
    Explanations

    assembled components

    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
    éĢ®
    -0.11
    æIJŃ
    -0.10
    æĴ¥
    -0.09
    åĩºè½¨
    -0.09
    é¹Ĭ
    -0.09
    åŁ¤
    -0.09
    éĢĴç»Ļ
    -0.09
    æ·ĺ
    -0.08
    æĭ¨
    -0.08
    伸åĩº
    -0.08
    POSITIVE LOGITS
    éĤ®
    0.09
    æĸĩ
    0.08
    械
    0.08
     Megan
    0.08
    éĿ¢
    0.08
    jom
    0.08
    pivot
    0.08
    éľľ
    0.08
    _parms
    0.08
    导弹
    0.08
    Activations Density 0.224%

    No Known Activations