© 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. 7389
    Prev
    Next
    INDEX
    Explanations

    mixed language or encodings

    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
    åŀ®
    -0.08
     Vide
    -0.07
    容
    -0.06
    æĢģ
    -0.06
    abah
    -0.06
    _static
    -0.06
    _video
    -0.06
    ä¸į失
    -0.06
    iston
    -0.06
    è¸ıå®ŀ
    -0.06
    POSITIVE LOGITS
    itos
    0.09
    aldi
    0.08
    çİĭçİī
    0.08
    å¼ķè¿°
    0.08
    çİĭå¿Ĺ
    0.08
     Angka
    0.08
    elper
    0.08
    æĢ»æķ°
    0.08
     تعب
    0.08
    æĹģè¾¹
    0.08
    Activations Density 0.007%

    No Known Activations