© 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. 7426
    Prev
    Next
    INDEX
    Explanations

    substrate stiffness, crystallinity, shell quality, font family

    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
    èĩªæĿ¥
    -0.07
    aky
    -0.07
    iani
    -0.07
    åı¤å±ĭ
    -0.07
    _mapped
    -0.07
    ión
    -0.07
    akest
    -0.07
    anser
    -0.07
    -dom
    -0.07
    _UNUSED
    -0.07
    POSITIVE LOGITS
     size
    0.11
    éķ¿åº¦
    0.11
     length
    0.10
    è´¨éĩıåĴĮ
    0.09
    è´¨éĩı
    0.09
    æķ°éĩıåĴĮ
    0.09
     characteristics
    0.09
    Size
    0.09
     Size
    0.09
    æĢ§è´¨
    0.09
    Activations Density 0.334%

    No Known Activations