© 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. 18494
    Prev
    Next
    INDEX
    Explanations

    sstream, times, Diplomate

    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
    elen
    -0.08
    eks
    -0.08
    esy
    -0.08
    ä¾Ŀæ³ķ追究责任
    -0.07
    aldi
    -0.07
    elsen
    -0.07
    eles
    -0.07
    ç½ijèģĶ
    -0.07
    alls
    -0.07
    opia
    -0.07
    POSITIVE LOGITS
     pháºŃn
    0.09
    ively
    0.08
    ible
    0.08
    mand
    0.08
    ühl
    0.07
    é¼»æ¶ķ
    0.07
    tures
    0.07
    antly
    0.07
    ãģ£ãģ±
    0.07
    סף
    0.07
    Activations Density 0.002%

    No Known Activations