© 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. 56112
    Prev
    Next
    INDEX
    Explanations

    ArcGIS GIS

    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
     boarded
    -0.10
    çŃ¾ç½²äºĨ
    -0.09
    åIJĥå¾Ĺ
    -0.09
    ä¸ĭ车
    -0.09
    åIJĬ
    -0.09
    åģĮ
    -0.08
    RootElement
    -0.08
    è¡ĮæĿİ
    -0.08
    åłĤ
    -0.08
    ä¸ĭåİ»
    -0.08
    POSITIVE LOGITS
    èıľ
    0.10
    æİ®
    0.09
    LOUR
    0.09
    idis
    0.09
     errorHandler
    0.08
    umped
    0.08
    临æŶ
    0.08
    æľīä¿¡å¿ĥ
    0.08
    _PD
    0.08
    ĵåIJį
    0.08
    Activations Density 0.128%

    No Known Activations