© 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. 3024
    Prev
    Next
    INDEX
    Explanations

    aims, teams, conditions, population, rule, cuts

    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
    ¿
    -0.07
    dap
    -0.07
    IZER
    -0.07
    fier
    -0.07
    jk
    -0.07
    ERI
    -0.07
    BED
    -0.07
    elib
    -0.06
    edy
    -0.06
     strconv
    -0.06
    POSITIVE LOGITS
    å³¥
    0.07
    æŀĹçĭ¬
    0.06
    åį³ä»¥
    0.06
    æĪIJçļĦ
    0.06
    èches
    0.06
    诸å¦Ĥ
    0.06
    inspace
    0.06
    sweise
    0.06
    æħķåIJį
    0.06
    åįĬ个
    0.06
    Activations Density 0.048%

    No Known Activations