© 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. 48617
    Prev
    Next
    INDEX
    Explanations

    blues and guitar

    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
    udios
    -0.09
    çļĦç¡®
    -0.09
    绾
    -0.09
    æĭĽ
    -0.09
    èĿ¼
    -0.09
    çµ®
    -0.09
    åĩĢæ°´
    -0.09
     ÐľÐ¾Ñģков
    -0.09
    èİ«æĸ¯ç§ij
    -0.09
    åIJĮäºĭ们
    -0.09
    POSITIVE LOGITS
    çĶ©
    0.10
    çĿĢæīĭ
    0.09
    çIJ¼
    0.09
    é¦Ĩ
    0.09
    Magn
    0.08
    çIJ¥
    0.08
    ä¸ŃæľŁ
    0.08
     midway
    0.08
     minor
    0.08
    åķ¸
    0.08
    Activations Density 0.188%

    No Known Activations