© 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. 8398
    Prev
    Next
    INDEX
    Explanations

    Information Act

    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
    åĪ©çļĦ
    -0.08
    ì§ĦìĿĢ
    -0.07
    ä½įç½®åĴĮ
    -0.07
    åĨħ容æľī
    -0.07
    èµĦæºIJåĴĮ
    -0.06
    èŀĥ
    -0.06
    å¼ĢåıijåĴĮ
    -0.06
    IOUS
    -0.06
    thouse
    -0.06
    åIJĪéĻ¢
    -0.06
    POSITIVE LOGITS
    æ°ı
    0.11
    æ³ķ
    0.10
    å¼ı
    0.09
    æ³ķçŃī
    0.08
    áºŃt
    0.08
    æľ¯
    0.08
    itis
    0.08
    erox
    0.08
    åŀĭ
    0.08
    idae
    0.07
    Activations Density 0.113%

    No Known Activations