© 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. 3282
    Prev
    Next
    INDEX
    Explanations

    portable devices and concepts

    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
    za
    -0.07
    èĩªå·±è¢«
    -0.07
    寿åħī
    -0.07
    æĿ¥ä¿¡
    -0.07
    çļĦ大éŨ
    -0.07
    apura
    -0.07
    èĿ¶éĺĢ
    -0.06
    hma
    -0.06
    dden
    -0.06
    cheduler
    -0.06
    POSITIVE LOGITS
     portable
    0.15
    /mobile
    0.14
    éļı身æIJºå¸¦
    0.13
    便æIJº
    0.13
    便æIJºå¼ı
    0.13
    Portable
    0.13
    éļı身
    0.12
    æIJºå¸¦
    0.12
    éļıè¡Į
    0.12
    mobile
    0.12
    Activations Density 0.330%

    No Known Activations