© 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. 50717
    Prev
    Next
    INDEX
    Explanations

    Airport names and locations

    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
    å±ħ士
    -0.07
    епен
    -0.07
    iqu
    -0.06
    ój
    -0.06
    ä¸įä¸Ĭ
    -0.06
    éĻ¶åĨ¶
    -0.06
     Vault
    -0.06
    ä¹Įé¾Ł
    -0.06
     prest
    -0.06
     ceramic
    -0.06
    POSITIVE LOGITS
     Arctic
    0.09
    thead
    0.09
    umberland
    0.09
    çİĽçijĻ
    0.08
    å¼ĢçªĹ
    0.08
    é¾Ļæ±Ł
    0.08
    undra
    0.08
    çĮİ人
    0.08
     Siber
    0.08
    貪
    0.08
    Activations Density 0.736%

    No Known Activations