© 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. 19841
    Prev
    Next
    INDEX
    Explanations

    matrix math notation

    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
    olen
    -0.07
     sub
    -0.07
    ouch
    -0.06
    ux
    -0.06
    éĸ
    -0.06
     subl
    -0.06
    able
    -0.06
    çĶ¨ä¸Ģ个
    -0.06
    ANDA
    -0.06
    ONO
    -0.06
    POSITIVE LOGITS
    funk
    0.09
    aggi
    0.08
     ÐļÑĢаÑģи
    0.08
    æĤ¨å·²ç»ı
    0.08
    esy
    0.07
    å°ijåħĪ
    0.07
    erden
    0.07
    Fone
    0.07
    .descriptor
    0.07
    entos
    0.07
    Activations Density 0.022%

    No Known Activations