© 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. 4539
    Prev
    Next
    INDEX
    Explanations

    man arrested after standoff

    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
    ä¸įä¼ļæľī
    -0.10
    æĪĸèĢħ说
    -0.09
     Flame
    -0.09
    ç»Ŀ对ä¸įä¼ļ
    -0.09
    å·¡åĽŀ
    -0.09
    éĩįå¡ij
    -0.08
    æ±¾
    -0.08
    çIJĨäºĭ
    -0.08
    æŃ¤é¡¹
    -0.08
    ä¸ĵé¢ĺ
    -0.08
    POSITIVE LOGITS
    lesh
    0.12
    çĭ¸
    0.09
    顶
    0.09
     Weinstein
    0.09
    zilla
    0.09
    Wo
    0.08
    éķ¿è¾¾
    0.08
    ä¸ĢåIJį
    0.08
    arius
    0.08
    /locale
    0.08
    Activations Density 0.242%

    No Known Activations