© 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. 49596
    Prev
    Next
    INDEX
    Explanations

    word or phrase introductions

    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
    ustum
    -0.07
    ÑĢид
    -0.07
    ynth
    -0.07
    षà¥į
    -0.07
    imme
    -0.07
    .persist
    -0.06
     pél
    -0.06
    οÏĢ
    -0.06
     floatValue
    -0.06
    éĤ£äºĽå¹´
    -0.06
    POSITIVE LOGITS
    çıŃ
    0.07
    eler
    0.07
    chet
    0.06
    sait
    0.06
     BOTH
    0.06
    Ł
    0.06
    éĢļåijĬ
    0.06
     trai
    0.06
    ab
    0.06
    rame
    0.06
    Activations Density 0.021%

    No Known Activations