© 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. 32525
    Prev
    Next
    INDEX
    Explanations

    systems and systems biology

    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
    éĵº
    -0.09
    å¹ķ
    -0.09
    çĶ¨éĩı
    -0.09
    æľĭ
    -0.08
    å±ķæľĽ
    -0.08
    jie
    -0.08
    ãģ£ãģ¡
    -0.08
    StreamWriter
    -0.08
    éĵºè®¾
    -0.08
    æĢĢ
    -0.08
    POSITIVE LOGITS
    ç³»ç»ŁçļĦ
    0.19
     systems
    0.17
    ç³»ç»Ł
    0.17
     system
    0.17
    ãĤ·ãĤ¹ãĥĨãĥł
    0.15
    系統
    0.15
     ÑģиÑģÑĤемÑĭ
    0.15
    .system
    0.15
     Systems
    0.14
     ÑģиÑģÑĤема
    0.14
    Activations Density 0.278%

    No Known Activations