© 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. 61402
    Prev
    Next
    INDEX
    Explanations

    numbers and word fragments

    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
    æĹ©åıijçİ°
    -0.08
    hini
    -0.08
    sker
    -0.07
     obsta
    -0.07
    isti
    -0.07
    碰碰
    -0.07
    è¢«æŁ¥
    -0.07
    ARIABLE
    -0.07
    ERVER
    -0.07
    BSD
    -0.07
    POSITIVE LOGITS
    ÑĤел
    0.07
    andle
    0.07
     electrical
    0.07
    den
    0.07
    izzle
    0.07
    æ±
    0.07
    onis
    0.06
    ondo
    0.06
    个
    0.06
    tron
    0.06
    Activations Density 0.001%

    No Known Activations