© 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. 19980
    Prev
    Next
    INDEX
    Explanations

    inbound pass, Knicks zone

    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
    轧
    -0.09
    广éĺĶ
    -0.09
    åĪ®
    -0.08
    ä¸Ģå¤ľ
    -0.08
    AMP
    -0.08
    æIJŃ
    -0.08
    ä¼ļåIJĮ
    -0.08
     epis
    -0.08
    (cards
    -0.08
    åĪĴ
    -0.08
    POSITIVE LOGITS
    á»ļ
    0.09
    achat
    0.09
    .ascii
    0.09
    èĤĩ
    0.09
    ç«łç¨ĭ
    0.08
    平常
    0.08
    ãģ£ãģ±
    0.08
    å¼Ĭ
    0.08
    ÐĤ
    0.08
    resco
    0.08
    Activations Density 0.018%

    No Known Activations