© 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. 21806
    Prev
    Next
    INDEX
    Explanations

    `(` or `)`` and numbers

    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
    acht
    -0.07
    á
    -0.07
     dahin
    -0.07
     seines
    -0.06
    ()-
    -0.06
    ainer
    -0.06
    zet
    -0.06
     nied
    -0.06
    èĮ¨
    -0.06
    구
    -0.06
    POSITIVE LOGITS
    ä¸Ķ
    0.09
    ä¸Ķæľī
    0.08
    ä¸Ķåľ¨
    0.08
    igator
    0.07
    igators
    0.07
    nish
    0.07
    _asc
    0.07
    ãģķãģ¾
    0.06
    anden
    0.06
     Ofer
    0.06
    Activations Density 0.004%

    No Known Activations