© 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. 2579
    Prev
    Next
    INDEX
    Explanations

    coffee roasting

    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
    ç§ĭ
    -0.09
    ä¸Ģç¢Ĺ
    -0.09
    åħīçݯ
    -0.09
    æŀľ
    -0.09
    åĬ¨çī©åĽŃ
    -0.09
    ÑģпоÑģоб
    -0.09
    ynes
    -0.08
    离
    -0.08
    ,en
    -0.08
    GLE
    -0.08
    POSITIVE LOGITS
    çİĦ
    0.09
    æīĵå¾Ĺ
    0.09
     esc
    0.09
    æ¡Ĥ
    0.09
    9
    0.09
    æķĽ
    0.09
    åĴ¬
    0.08
    odash
    0.08
    åĬłçĽŁåºĹ
    0.08
    çĦī
    0.08
    Activations Density 0.034%

    No Known Activations