© 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. 32744
    Prev
    Next
    INDEX
    Explanations

    HTML, shell, or UI elements

    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
    åħļçļĦäºĮåįģ大
    -0.07
    ello
    -0.07
    ä¸Ĭæµ·åĽ½éĻħ
    -0.07
    ppure
    -0.07
    thers
    -0.07
    Ø©
    -0.07
    <decltype
    -0.07
    ÙİÙij
    -0.07
    ÃŁe
    -0.06
    ÙijÙĩ
    -0.06
    POSITIVE LOGITS
    usercontent
    0.08
    áp
    0.07
    etje
    0.07
    kerne
    0.07
    InputStream
    0.07
    åħ®
    0.06
    locker
    0.06
    filer
    0.06
    ਾà¨Ĥ
    0.06
    üter
    0.06
    Activations Density 0.206%

    No Known Activations