© 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. 49035
    Prev
    Next
    INDEX
    Explanations

    frequency and Hz

    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
    麻éĽĢ
    -0.08
    blink
    -0.08
    busy
    -0.07
    èĮĹ
    -0.07
    hely
    -0.07
    稼
    -0.07
    æĬĹæ°§åĮĸ
    -0.07
    Busy
    -0.07
    ikip
    -0.07
     streamlined
    -0.06
    POSITIVE LOGITS
    éļĪ
    0.08
    ä¸įæĪIJ
    0.07
    为主çļĦ
    0.07
     доно
    0.07
    åݿ人æ°ijæ³ķéĻ¢
    0.07
    ernt
    0.07
     (_)
    0.07
     frequencies
    0.07
    ason
    0.07
    imos
    0.07
    Activations Density 0.024%

    No Known Activations