© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14828
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or equations

    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
    verso
    -0.08
    elay
    -0.08
    oran
    -0.08
     redesigned
    -0.08
    inal
    -0.07
    anela
    -0.07
    _gem
    -0.07
    anto
    -0.07
    عÙĪ
    -0.07
    arden
    -0.07
    POSITIVE LOGITS
    åĨ²åĪº
    0.07
    resar
    0.06
    fa
    0.06
    亲åĴĮ
    0.06
    éĴĿ
    0.06
    afc
    0.06
    ãģ¿ãģª
    0.06
    component
    0.06
    éĢĤå½ĵ
    0.06
    æľĿ天
    0.06
    Activations Density 0.004%

    No Known Activations