© 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. 37686
    Prev
    Next
    INDEX
    Explanations

    thinking about

    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
     lyon
    -0.11
    estre
    -0.10
    ä¸ĭåİ»
    -0.09
    .DependencyInjection
    -0.09
    .Enum
    -0.08
    iaux
    -0.08
    å¾ģ
    -0.08
    Õ¬
    -0.08
    å®®
    -0.08
    æ²ī
    -0.08
    POSITIVE LOGITS
    æĬĬè¿Ļ个
    0.11
    马ä¸Ĭ
    0.10
    æijĩ头
    0.10
    éĢĴç»Ļ
    0.10
    读èĢħ
    0.10
    åIJ¬å®Į
    0.10
    è¾ĸ
    0.09
    .variables
    0.09
    jur
    0.09
    ays
    0.09
    Activations Density 0.046%

    No Known Activations