© 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. 63681
    Prev
    Next
    INDEX
    Explanations

    Scottish geography, programming, biology terms

    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
    OOD
    -0.08
    ucas
    -0.08
    astr
    -0.08
    èݹ
    -0.07
    _note
    -0.07
    æµ·å¸Ĥ
    -0.07
    .two
    -0.07
    çĵ
    -0.07
    vÄĽ
    -0.07
    ÙĨاس
    -0.07
    POSITIVE LOGITS
    -helper
    0.06
    å¯Ĵ
    0.06
    strip
    0.06
    IME
    0.06
    ฤ
    0.06
    çŃĭ
    0.06
    æĶ¾ç½®
    0.06
     advent
    0.06
    rase
    0.06
    å°ıç¼ĸ
    0.06
    Activations Density 0.568%

    No Known Activations