© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 64071
    Prev
    Next
    INDEX
    Explanations

    mathematical notation or code blocks

    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
    ibli
    -0.09
    documento
    -0.08
    'http
    -0.07
    estring
    -0.07
    bower
    -0.07
    ciare
    -0.07
    WEBPACK
    -0.07
    acer
    -0.07
    &A
    -0.07
    ACHED
    -0.07
    POSITIVE LOGITS
    建档
    0.06
    祷
    0.06
    Ĵ
    0.06
    ÑĢак
    0.06
    eto
    0.06
    der
    0.06
    åĦ¿çļĦ
    0.06
    è°IJ
    0.06
    0.06
    姻
    0.06
    Activations Density 0.012%

    No Known Activations