© 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. 33289
    Prev
    Next
    INDEX
    Explanations

    parentheses and special characters

    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
    ↵        ↵        ↵
    -0.08
    cept
    -0.07
    ï¬ģ
    -0.07
    ideon
    -0.07
    cest
    -0.07
    ignon
    -0.06
    ...).
    -0.06
    schrift
    -0.06
    ior
    -0.06
    ÐijУ
    -0.06
    POSITIVE LOGITS
    èī²åĪĹ
    0.09
    zelf
    0.09
    à¹īำ
    0.09
    luk
    0.07
    ONGL
    0.07
    enca
    0.07
    kowych
    0.07
    irected
    0.07
    stående
    0.07
    aur
    0.07
    Activations Density 0.417%

    No Known Activations