© 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. 32502
    Prev
    Next
    INDEX
    Explanations

    variable names and code keywords

    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
    ictionary
    -0.08
    çĿ¹
    -0.07
    MOTE
    -0.07
    nant
    -0.07
    ä½ľè¯į
    -0.07
    .cn
    -0.07
    ibera
    -0.07
    裸
    -0.07
    çıłä¸īè§Ĵ
    -0.07
    JNI
    -0.07
    POSITIVE LOGITS
    cana
    0.08
    é«ĺçŃī
    0.07
    ed
    0.07
    天主æķĻ
    0.07
    dd
    0.07
    æİ¥è¿ij
    0.07
    ilding
    0.06
     Ani
    0.06
    ưỡng
    0.06
    姿
    0.06
    Activations Density 0.004%

    No Known Activations