© 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. 54407
    Prev
    Next
    INDEX
    Explanations

    locations or structures

    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
    离ä¸įå¼Ģ
    -0.09
    ãģ¨ãģĦãģĨãģĵãģ¨
    -0.09
     means
    -0.08
    乡
    -0.08
    ä¹ĭ乡
    -0.08
    ToDo
    -0.08
    ÑģÑı
    -0.08
    TV
    -0.08
    éĤij
    -0.08
     Hä
    -0.07
    POSITIVE LOGITS
    schlü
    0.09
     Barcl
    0.09
    èķ¨
    0.09
    ulton
    0.09
    ainty
    0.09
    åѦçĶŁä»¬
    0.08
    æĶ¯æĮģåĬĽåº¦
    0.08
     refusal
    0.08
    èıł
    0.08
    ACEMENT
    0.08
    Activations Density 0.150%

    No Known Activations