© 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. 44091
    Prev
    Next
    INDEX
    Explanations

    hexadecimal numbers

    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
    ing
    -0.10
    en
    -0.10
    y
    -0.08
    iš
    -0.08
    æĸ°åĬłåĿ¡
    -0.08
    enje
    -0.08
    eenth
    -0.08
    s
    -0.08
    Ø©
    -0.07
    aing
    -0.07
    POSITIVE LOGITS
    ìį¨
    0.08
    ë¦Ħ
    0.08
    gada
    0.08
    gadas
    0.08
    artigen
    0.07
    éĢļè¿ĩè¿Ļ次
    0.07
    ê°Ģê°Ģ
    0.07
    artige
    0.07
    ramid
    0.07
    anness
    0.07
    Activations Density 0.028%

    No Known Activations