© 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. 15919
    Prev
    Next
    INDEX
    Explanations

    charting

    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
    er
    -0.11
    hart
    -0.10
    Ùħ
    -0.09
    hip
    -0.09
    hafte
    -0.09
    had
    -0.09
    have
    -0.09
    ettes
    -0.09
    ható
    -0.09
    hoz
    -0.09
    POSITIVE LOGITS
    ting
    0.19
    ypes
    0.18
    aylor
    0.17
    ãĤ¥
    0.16
    unnel
    0.16
    esseract
    0.14
    emplates
    0.13
    oulouse
    0.13
    utorial
    0.13
    tingham
    0.13
    Activations Density 3.952%

    No Known Activations