© 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. 22246
    Prev
    Next
    INDEX
    Explanations

    geographical locations and technical terms

    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
     Corm
    -0.07
    èݹ
    -0.07
    n
    -0.06
    缸äºĴ
    -0.06
     Bel
    -0.06
    æĺķ
    -0.06
    ieux
    -0.06
    plx
    -0.06
    azy
    -0.06
    <small
    -0.06
    POSITIVE LOGITS
    ventional
    0.08
    _google
    0.08
    LIB
    0.07
     terrest
    0.07
     conventional
    0.07
    èİŀ
    0.07
    wik
    0.07
    æĻ®éĢļãģ«
    0.07
    >Please
    0.07
    åĦ¿åŃIJçļĦ
    0.07
    Activations Density 0.617%

    No Known Activations