© 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. 40532
    Prev
    Next
    INDEX
    Explanations

    $ variable markers

    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
    ore
    -0.07
    æ³Ľèµ·
    -0.06
    onte
    -0.06
    ÙĥÙĬÙĨ
    -0.06
    èĤ¡æĿĥè´¨æĬ¼
    -0.06
    大æ¦Ĥ
    -0.06
    éĤ£ä»ĸ
    -0.06
    exual
    -0.06
    ÅĤod
    -0.06
     Pue
    -0.06
    POSITIVE LOGITS
    άλ
    0.08
    abor
    0.07
    اÙħ
    0.07
    æľ¬æĸĩæĿ¥èĩª
    0.07
    issen
    0.07
    æľīçĶŁ
    0.07
    lef
    0.07
    lice
    0.07
    insi
    0.07
    asian
    0.07
    Activations Density 0.003%

    No Known Activations