© 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. 47232
    Prev
    Next
    INDEX
    Explanations

    distance, entropy, transport, information

    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
    ÑĪеб
    -0.07
    obox
    -0.06
    æĥ³ä½ł
    -0.06
     Grat
    -0.06
    ç³»
    -0.06
    è¿Ļæł¹
    -0.06
    ä¼łçļĦ
    -0.06
    æĮł
    -0.06
    /function
    -0.06
     gir
    -0.06
    POSITIVE LOGITS
    elihood
    0.09
    çĨĻ
    0.09
     Mutual
    0.08
    utzer
    0.08
    angel
    0.08
     mutual
    0.08
    大ç¥ŀ
    0.07
    ç¥ŀä¹ĭ
    0.07
    æĸ°èĢģ
    0.07
    åĪ¤åĨ³
    0.07
    Activations Density 0.010%

    No Known Activations