© 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. 50990
    Prev
    Next
    INDEX
    Explanations

    biographies or place names

    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
    reff
    -0.11
    ìĤ¬íķŃ
    -0.10
    æĿĻ
    -0.09
    еÑĩно
    -0.09
    äºĮåŃĹ
    -0.09
    icap
    -0.09
    iful
    -0.09
    æĹłçŁ¥
    -0.09
    intl
    -0.09
    橱
    -0.09
    POSITIVE LOGITS
    çķĶ
    0.12
    éºĵ
    0.09
     “
    0.09
    å¼ıçļĦ
    0.08
    顺
    0.08
    à¹Į
    0.08
     proverb
    0.08
    orem
    0.08
    âĢ¦
    0.08
    ads
    0.07
    Activations Density 1.724%

    No Known Activations