© 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. 40877
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    èıľåĽŃ
    -0.08
    adge
    -0.07
    ÙĬÙĨا
    -0.07
    alth
    -0.07
    æ¾ľ
    -0.07
    ôme
    -0.07
    ÑĹв
    -0.07
    ottage
    -0.07
     ineff
    -0.07
    меÑģÑĤи
    -0.07
    POSITIVE LOGITS
    teras
    0.07
    åIJĮæŶè¿ĺè¦ģ
    0.07
    acara
    0.07
    æĽĻ
    0.07
    amin
    0.07
    rij
    0.06
    תר
    0.06
    اÙĨس
    0.06
    arer
    0.06
    heimer
    0.06
    Activations Density 0.518%

    No Known Activations