© 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. 30875
    Prev
    Next
    INDEX
    Explanations

    list item separators followed by names

    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
    ä¹Łæľīä¸ĢäºĽ
    -0.10
    çī²
    -0.09
    åľ¨é¦Ļ港
    -0.09
    oth
    -0.09
    æĵ¦
    -0.09
    æĿijæ°ij们
    -0.09
    èĤĭ
    -0.09
    å¼Ń
    -0.08
    对ä¼ģä¸ļ
    -0.08
    åľ¨æ·±åľ³
    -0.08
    POSITIVE LOGITS
    éĺ´
    0.09
    åIJĦ个
    0.09
    æĹ¥è®°
    0.09
     ÑģÑĩиÑĤа
    0.08
    éĵľ
    0.08
    æĦ¿æĦı
    0.08
    èĢĺ
    0.08
    åıªæľī
    0.08
     Millennium
    0.08
     Vision
    0.07
    Activations Density 0.100%

    No Known Activations