© 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. 22429
    Prev
    Next
    INDEX
    Explanations

    Core followed by OS or tip

    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
    oriously
    -0.09
    soever
    -0.08
    Ø©
    -0.08
    iable
    -0.08
    zelf
    -0.08
    ziger
    -0.07
    اتÙĩا
    -0.07
    enny
    -0.07
     Ahli
    -0.07
    ively
    -0.07
    POSITIVE LOGITS
    less
    0.11
    lessly
    0.09
    ystal
    0.08
    aceous
    0.08
    lessness
    0.08
    lement
    0.08
    ption
    0.08
    langs
    0.07
    ä½ij
    0.07
    ursive
    0.07
    Activations Density 0.035%

    No Known Activations