© 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. 55418
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and symbols

    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
    Įĵ
    -0.06
    agher
    -0.06
    ervers
    -0.06
    _idxs
    -0.06
    idden
    -0.06
    (Il
    -0.06
    对åı£
    -0.06
     Schon
    -0.06
    ÙħÙħ
    -0.06
    \xc
    -0.06
    POSITIVE LOGITS
    ÙĴÙĬ
    0.07
    .ru
    0.07
    ÙĪص
    0.07
    ži
    0.07
    spath
    0.07
    çijľ
    0.07
    ikal
    0.06
    fter
    0.06
    éĿ¢ãģ«
    0.06
    žit
    0.06
    Activations Density 0.018%

    No Known Activations