© 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. 62715
    Prev
    Next
    INDEX
    Explanations

    Jalisco, Zacatecas, Mexico

    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
    ICS
    -0.10
    à¹Ĥà¸Ľà¸£à¸Ķ
    -0.09
    лег
    -0.08
    åĽ½å®¶å®īåħ¨
    -0.08
     Bedford
    -0.08
    ä¸ĢæŶ
    -0.08
    ÑģÑı
    -0.08
    _inactive
    -0.08
     Basil
    -0.08
    .ASCII
    -0.08
    POSITIVE LOGITS
    èļĵ
    0.10
    潮湿
    0.09
    æĪijä¸įçŁ¥éģĵ
    0.09
    æī§æķĻ
    0.09
    çĵ¶åŃIJ
    0.09
    足
    0.09
    æĭ§
    0.09
    ean
    0.09
    oro
    0.08
    åĶ³
    0.08
    Activations Density 0.038%

    No Known Activations