© 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. 31296
    Prev
    Next
    INDEX
    Explanations

    collector's item or collectibles

    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
    acha
    -0.09
    åĨ³ä¸į
    -0.08
    åĨ»
    -0.08
    åªĴ
    -0.08
    使çĶ¨èĢħ
    -0.08
    人人éĥ½
    -0.07
    é¦Ļåij³
    -0.07
    onders
    -0.07
    éĢı
    -0.07
    MENT
    -0.07
    POSITIVE LOGITS
    (Collectors
    0.09
     Dah
    0.09
    屿
    0.09
    åѦä¼ļäºĨ
    0.09
    天涯
    0.09
    ä¹ĭå¿ĥ
    0.09
    inde
    0.09
    å¢ŀæ·»äºĨ
    0.09
    ç²īç¢İ
    0.09
     ÐĴедÑĮ
    0.08
    Activations Density 0.012%

    No Known Activations