© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53906
    Prev
    Next
    INDEX
    Explanations

    suffix "-aries"

    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
    éĤ£ä½į
    -0.10
    ellar
    -0.09
    ptrdiff
    -0.08
    åIJĮä¼´
    -0.08
    iram
    -0.08
    ä»Ĺ
    -0.08
    opher
    -0.08
    èĨĽ
    -0.08
    åĩºæīĭ
    -0.08
    æĢĻ
    -0.08
    POSITIVE LOGITS
    èĮ¬
    0.10
    为åħ¶
    0.09
    digest
    0.09
    请注æĦı
    0.09
    ä¸įéĶĪ
    0.09
    éĵ¿
    0.09
    éĤĪ
    0.09
    isin
    0.09
    éĴ®
    0.09
    _EOL
    0.08
    Activations Density 0.001%

    No Known Activations