© 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. 34510
    Prev
    Next
    INDEX
    Explanations

    hereinafter

    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
    غار
    -0.08
    colar
    -0.07
     Kushner
    -0.07
    Ñĩенко
    -0.07
    inker
    -0.06
    andu
    -0.06
    åħ¸
    -0.06
    æ»
    -0.06
    aglia
    -0.06
    æ½¢
    -0.06
    POSITIVE LOGITS
    yı
    0.07
    fone
    0.07
    ."\
    0.06
     "('
    0.06
     rév
    0.06
    KeyName
    0.06
    ondre
    0.06
    иÑĤелÑĮно
    0.06
    ÙĬÙĭا
    0.06
    маÑĤÑĭ
    0.06
    Activations Density 0.006%

    No Known Activations