© 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. 26564
    Prev
    Next
    INDEX
    Explanations

    technical documentation

    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
    øl
    -0.08
    æı´æľĿ
    -0.08
    åį³åĪ°
    -0.07
    VRT
    -0.07
    atalog
    -0.07
    å¢Ł
    -0.07
    \""
    -0.07
    ÙĴرÙIJ
    -0.07
    encent
    -0.07
    iagnostics
    -0.07
    POSITIVE LOGITS
    ohen
    0.06
    жем
    0.06
    ¨
    0.06
     Propel
    0.06
    è¯ŃéŁ³æŶéķ¿
    0.06
    iever
    0.06
    ÑĴе
    0.06
    ãģ¹ãģį
    0.06
    è¿Ī
    0.06
    amos
    0.06
    Activations Density 0.001%

    No Known Activations