© 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. 54964
    Prev
    Next
    INDEX
    Explanations

    educational institutions and affiliations

    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
    INES
    -0.10
    çµ®
    -0.10
    è¦Ĩ
    -0.10
    仪表
    -0.09
    cpy
    -0.09
    èĬĥ
    -0.09
    ÑijÑĢ
    -0.09
    仪
    -0.09
    ctp
    -0.09
    æĹ¥æŃ£å¼ı
    -0.09
    POSITIVE LOGITS
    åIJįæł¡
    0.18
    顶å°ĸ
    0.11
    ä¸Ģæµģ
    0.11
    ç²¾èĭ±
    0.11
    åIJįçīĮ
    0.10
    ä¸ĸçķĮä¸Ģæµģ
    0.10
     prestigious
    0.10
    èľļ
    0.10
    éĻ¢æł¡
    0.10
    åĵĪä½Ľ
    0.09
    Activations Density 0.039%

    No Known Activations