© 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. 10788
    Prev
    Next
    INDEX
    Explanations

    design files and settings

    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
    orn
    -0.09
    æĮ¨
    -0.09
     Amir
    -0.08
     JsonRequest
    -0.08
    ä¸įæĸŃå¢ŀåĬł
    -0.08
    ORN
    -0.08
    æ·¡å®ļ
    -0.08
    æľ¬çĿĢ
    -0.08
    _BASIC
    -0.08
     Parad
    -0.08
    POSITIVE LOGITS
    æĶ¶åĽŀ
    0.09
    æ¸ij
    0.09
    稿
    0.09
     ÑģвÑıзи
    0.09
    å°ıå·§
    0.08
    计åħ¥
    0.08
    é¾Ħ
    0.08
    DataManager
    0.08
    å¯Ħæīĺ
    0.08
    è¿ĺæľīä»Ģä¹Ī
    0.08
    Activations Density 0.398%

    No Known Activations