© 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. 60494
    Prev
    Next
    INDEX
    Explanations

    p, +, pauses, license

    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
     Imp
    -0.07
     zw
    -0.06
    ä¾Ŀæ³ķèĩªä¸»
    -0.06
    Imp
    -0.06
     stagger
    -0.06
    ä¼ģä¸ļæ³ķ人
    -0.06
    pont
    -0.06
    Õ¾
    -0.06
    è¾¾å°Ķ
    -0.06
    åį¸è½½
    -0.06
    POSITIVE LOGITS
    kening
    0.08
    é»į
    0.08
    oven
    0.07
    kti
    0.07
    oves
    0.07
    akte
    0.07
     nhi
    0.07
     Coro
    0.07
    isha
    0.07
    ikti
    0.07
    Activations Density 0.256%

    No Known Activations