© 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. 10203
    Prev
    Next
    INDEX
    Explanations

    conversion

    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
    ç³Ł
    -0.12
    æĭ¼
    -0.08
    éĩijèŀįå¸Ĥåľº
    -0.08
    çļİ
    -0.08
     Everyday
    -0.08
    平常
    -0.08
    ä¸įæĸŃåıijå±ķ
    -0.08
    Paste
    -0.08
    quet
    -0.08
    n
    -0.08
    POSITIVE LOGITS
    转åĮĸ
    0.13
    转åĮĸ为
    0.11
     conversion
    0.11
    conversion
    0.11
     CONVERT
    0.10
     Converts
    0.10
    _CONVERT
    0.10
    åĵºä¹³
    0.10
    Conversion
    0.09
    çķĻä½ı
    0.09
    Activations Density 0.064%

    No Known Activations