© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 3350
    Prev
    Next
    INDEX
    Explanations

    most among best fastest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adou
    -0.08
    lassen
    -0.07
    _UNSIGNED
    -0.07
     vorba
    -0.07
    åı¯æĢķçļĦæĺ¯
    -0.07
    asang
    -0.07
    ä»ij
    -0.07
    使çĶ¨çļĦæĺ¯
    -0.07
     vidare
    -0.07
    áĥĶáĥľ
    -0.07
    POSITIVE LOGITS
     most
    0.11
     among
    0.11
     пожалÑĥй
    0.10
    æĪijæľĢ
    0.10
     ê°Ģìŀ¥
    0.10
    æľĢ
    0.10
    æľĢ为
    0.09
    ä¸ĸçķĮä¸ĬæľĢ
    0.09
    æľĢãĤĤ
    0.09
    ä¸ŃæľĢ
    0.09
    Activations Density 0.907%

    No Known Activations