© 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. 52413
    Prev
    Next
    INDEX
    Explanations

    required by law or obligation free

    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
    æīĵäºĨ
    -0.09
    runner
    -0.09
    åĨľåī¯äº§åĵģ
    -0.09
    æ¯ķ
    -0.08
    Gre
    -0.08
     Greene
    -0.08
    åĪ¤
    -0.08
    注åĨĮèµĦæľ¬
    -0.08
    odo
    -0.08
    ReadWrite
    -0.08
    POSITIVE LOGITS
    ìŀ¥ìĿĦ
    0.10
    串
    0.10
    ìŀ¥
    0.09
    vais
    0.09
    éĤ¸
    0.09
    иÑĤел
    0.09
    çħ§æĸĻ
    0.09
    aternity
    0.08
    è¿ĩ
    0.08
    æŃ¢
    0.08
    Activations Density 0.009%

    No Known Activations