© 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. 10462
    Prev
    Next
    INDEX
    Explanations

    mathematical fractions or arrays

    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
    гли
    -0.07
    éĿĵ
    -0.06
    æĻĮ
    -0.06
    æĤ²æ¬¢
    -0.06
    iren
    -0.06
    af
    -0.06
    éĨīäºĨ
    -0.06
    uke
    -0.06
    ugin
    -0.06
    grounds
    -0.06
    POSITIVE LOGITS
    bsites
    0.08
    åĬłè½½æĽ´å¤ļ
    0.08
    åįģä¸ĩ
    0.08
    åħ¶æŀĹ
    0.07
     Hera
    0.07
    BIND
    0.07
    perk
    0.07
    _exc
    0.07
     somew
    0.07
    itada
    0.07
    Activations Density 0.008%

    No Known Activations