© 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. 33338
    Prev
    Next
    INDEX
    Explanations

    angular units: degrees, minutes, arc

    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
    è¿ĺåİŁ
    -0.08
    åij±åij±
    -0.08
    åįģä¸Ģç«ł
    -0.07
    sville
    -0.07
    ewater
    -0.07
     Romagna
    -0.07
    è§ģè¯ģ
    -0.07
    ä¸ŃåİŁ
    -0.07
    æ±
    -0.07
    éĺ´
    -0.07
    POSITIVE LOGITS
     subt
    0.08
    /google
    0.07
    æķ£äºĨ
    0.07
    [opt
    0.07
    æĶ¾å¤§éķľ
    0.07
     Amateur
    0.07
     aberr
    0.07
    弧度
    0.07
    wander
    0.07
    optic
    0.07
    Activations Density 0.003%

    No Known Activations