© 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. 20059
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation in lists

    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
    liest
    -0.07
     tract
    -0.06
    ãģªãģį
    -0.06
    kest
    -0.06
     jac
    -0.06
     forth
    -0.06
    .free
    -0.06
    inqu
    -0.06
    ng
    -0.06
    è«ĩ
    -0.06
    POSITIVE LOGITS
    PushButton
    0.07
    ega
    0.07
    YLE
    0.07
    åºı
    0.07
    æİ
    0.07
    eksi
    0.07
    iaux
    0.07
    gio
    0.07
    acements
    0.07
    lex
    0.07
    Activations Density 0.016%

    No Known Activations