© 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. 50626
    Prev
    Next
    INDEX
    Explanations

    Administration, government, union

    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
    为é¦ĸ
    -0.09
    -addons
    -0.09
    顺
    -0.08
    çłĶ究æĬ¥åijĬ
    -0.08
    è´¦
    -0.08
    æĬĢæľ¯æ°´å¹³
    -0.08
    æĸ°æ¬¾
    -0.08
    ç»Ĭ
    -0.08
    inverse
    -0.08
    æĺ¯æĢİæł·
    -0.08
    POSITIVE LOGITS
    cls
    0.10
    åĥį
    0.10
    eding
    0.10
    æī¾å·¥ä½ľ
    0.10
    å¨ī
    0.09
    å·¥ä½ľèĢħ
    0.09
    Tro
    0.09
    é£İåı£
    0.09
    è°Ľ
    0.09
    篮
    0.09
    Activations Density 0.147%

    No Known Activations