© 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. 3182
    Prev
    Next
    INDEX
    Explanations

    click, grab, navigate, switch

    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
    è´´
    -0.09
    _deinit
    -0.09
    iped
    -0.09
    .EMAIL
    -0.09
    bro
    -0.09
    帮
    -0.09
    uria
    -0.09
     Fruit
    -0.09
    nett
    -0.08
    OutOfRangeException
    -0.08
    POSITIVE LOGITS
    符åIJĪæĿ¡ä»¶
    0.09
    便åı¯
    0.09
    ä¼ļåĩºçİ°
    0.09
    éħįä¸Ĭ
    0.09
    æİī
    0.08
    вод
    0.08
    éĤ£åĦ¿
    0.08
    éĩĮéĿ¢æľī
    0.08
    3
    0.08
    便ä¼ļ
    0.08
    Activations Density 0.088%

    No Known Activations