© 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. 14043
    Prev
    Next
    INDEX
    Explanations

    linking with files or code

    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
    æĦıæ°Ķ
    -0.07
    ä¸ij
    -0.07
    æīĢ以对äºİ
    -0.07
    ihi
    -0.06
    uest
    -0.06
    _suite
    -0.06
    èĥ
    -0.06
     gh
    -0.06
     Submitted
    -0.06
    /fw
    -0.06
    POSITIVE LOGITS
    NotFoundError
    0.07
    _mx
    0.07
    NotFoundException
    0.07
     presently
    0.07
    currently
    0.07
    _DOC
    0.07
     **#
    0.07
    øv
    0.07
     previously
    0.07
     cerem
    0.07
    Activations Density 0.002%

    No Known Activations