© 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. 65450
    Prev
    Next
    INDEX
    Explanations

    realism and representation

    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
    occa
    -0.08
    åįķæīĭ
    -0.08
    ç½ijç«Ļ导èĪª
    -0.07
    ÏĢÏĦÏħ
    -0.07
    WithValue
    -0.07
    讼
    -0.07
    urras
    -0.07
    antin
    -0.07
    è¿IJçŃ¹
    -0.07
    ç§ģç«ĭ
    -0.07
    POSITIVE LOGITS
    羣å®ŀ
    0.13
    羣å®ŀæĢ§
    0.13
    å¿łå®ŀ
    0.12
    è¿ĺåİŁ
    0.12
     authenticity
    0.11
    羣å®ŀçļĦ
    0.11
    (real
    0.11
    -real
    0.11
    åĨĻå®ŀ
    0.10
    æ±Ĥ羣
    0.10
    Activations Density 0.119%

    No Known Activations