© 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. 47839
    Prev
    Next
    INDEX
    Explanations

    thinking about something

    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
    isode
    -0.07
    amen
    -0.07
    evoli
    -0.07
     Inhalts
    -0.07
    fffffff
    -0.07
    egi
    -0.07
    ToDevice
    -0.07
    utica
    -0.07
    ä¸įé½IJ
    -0.06
    ména
    -0.06
    POSITIVE LOGITS
    并åıijå¸ĥ
    0.14
    并å°Ĩ
    0.12
    并
    0.12
    并å°Ĩåħ¶
    0.12
    并ç»Ħç»ĩ
    0.12
    并以
    0.12
    å¹¶åľ¨
    0.11
    并æĬ¥
    0.11
    并åIJij
    0.11
    并ä¿ĿæĮģ
    0.11
    Activations Density 0.506%

    No Known Activations