© 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. 62602
    Prev
    Next
    INDEX
    Explanations

    classification types and series

    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
    ë¡Ŀ
    -0.07
    áĥĽáĥIJ
    -0.07
     اÙĦØ«
    -0.06
    amment
    -0.06
    æĺ¯ä»¶
    -0.06
    ä½ľä¸ºä¸Ģ项
    -0.06
     vét
    -0.06
    ãĪľ
    -0.06
    ä¸Ģç¬Ķ
    -0.06
    enor
    -0.06
    POSITIVE LOGITS
     designation
    0.09
     subtype
    0.09
     subclass
    0.09
    ä¸īç±»
    0.09
    åĴĮ第
    0.08
    /type
    0.08
     category
    0.08
    ınıf
    0.08
    type
    0.08
    ç·»
    0.08
    Activations Density 0.217%

    No Known Activations