© 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. 47747
    Prev
    Next
    INDEX
    Explanations

    Georgia and Google LLC/Inc

    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
     Winnipeg
    -0.09
     Manitoba
    -0.08
    西æ¹ĸ
    -0.08
    æ´±
    -0.07
     Trafford
    -0.07
    çĥ
    -0.07
     recharge
    -0.07
     Manit
    -0.07
    西å®ģ
    -0.07
     Spokane
    -0.06
    POSITIVE LOGITS
    .google
    0.17
    Google
    0.16
    google
    0.16
     google
    0.16
     Georgia
    0.16
    Georgia
    0.15
    /google
    0.15
    -google
    0.15
    goog
    0.15
     Google
    0.15
    Activations Density 1.081%

    No Known Activations