© 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. 21477
    Prev
    Next
    INDEX
    Explanations

    "is a"

    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
    prite
    -0.09
    .dot
    -0.08
    Ñĩем
    -0.08
    .Excel
    -0.08
    entin
    -0.08
    æį®æѤ
    -0.08
    رÙģ
    -0.08
    å¥
    -0.08
    ersh
    -0.08
    èĢĮåİ»
    -0.08
    POSITIVE LOGITS
    æĤ¼
    0.09
    å¥ī
    0.09
    æĪĴ
    0.09
    å¸ĸ
    0.09
    ัà¸į
    0.08
     pedest
    0.08
    纪
    0.08
    纯粹
    0.08
    åijĬè¯ī
    0.08
    æŨ
    0.08
    Activations Density 0.106%

    No Known Activations