© 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. 32663
    Prev
    Next
    INDEX
    Explanations

    spaces and design

    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
     Goldberg
    -0.09
    纯æ´ģ
    -0.09
    纲
    -0.09
     skeleton
    -0.08
     Disp
    -0.08
    éĢī
    -0.08
    ç®ĹäºĨ
    -0.08
    uda
    -0.08
    éĿ¢èĨľ
    -0.08
    vana
    -0.08
    POSITIVE LOGITS
    尺度
    0.14
    Spaces
    0.12
    ä¸Ńå°ı
    0.11
    ä»¥äººä¸ºæľ¬
    0.09
    çļĦåıijçĶŁ
    0.09
    ä¸Ńå°ıåŀĭ
    0.09
    çĨĻ
    0.09
     Spaces
    0.09
    ä¸Ńå°ıä¼ģä¸ļ
    0.09
    以人为
    0.09
    Activations Density 0.064%

    No Known Activations