© 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. 47608
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by sentence start

    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
    uzz
    -0.07
    e
    -0.07
    ism
    -0.06
    寰
    -0.06
    çģ
    -0.06
     and
    -0.06
    Ì
    -0.06
    ir
    -0.06
    浪
    -0.06
    ang
    -0.06
    POSITIVE LOGITS
    ÑĢика
    0.08
    APH
    0.08
    zol
    0.08
    etas
    0.08
    оÑģÑģ
    0.08
    elib
    0.08
    _each
    0.08
    ovid
    0.08
    ours
    0.08
    -cols
    0.08
    Activations Density 0.091%

    No Known Activations