© 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. 3608
    Prev
    Next
    INDEX
    Explanations

    counts within parentheses (n=)

    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
    awat
    -0.08
    kow
    -0.07
    psc
    -0.07
     pros
    -0.07
    etto
    -0.07
    æ¡¥éķĩ
    -0.06
    vinc
    -0.06
    riage
    -0.06
    .sig
    -0.06
    ibar
    -0.06
    POSITIVE LOGITS
    .sourceforge
    0.08
    lte
    0.08
    åī©ä¸ĭ
    0.07
    عار
    0.07
    sä
    0.07
    áºŃy
    0.07
    lare
    0.07
     heel
    0.07
    æĻ©
    0.07
    áro
    0.07
    Activations Density 0.107%

    No Known Activations