© 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. 19076
    Prev
    Next
    INDEX
    Explanations

    hexadecimal identifiers

    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
    &W
    -0.08
    ظ
    -0.07
    jung
    -0.07
    ÙĩÙı
    -0.07
    ock
    -0.07
     جÙĪر
    -0.06
    &T
    -0.06
    CTL
    -0.06
    åĵ©
    -0.06
    enberg
    -0.06
    POSITIVE LOGITS
    inte
    0.07
    arias
    0.07
    utre
    0.07
     Firma
    0.06
     Firmen
    0.06
    åIJĦ个æĸ¹éĿ¢
    0.06
    amenti
    0.06
    ارÙĬÙĨ
    0.06
    çĢ
    0.06
    ANCH
    0.06
    Activations Density 0.041%

    No Known Activations