© 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. 58121
    Prev
    Next
    INDEX
    Explanations

    crew working, squad for, parents, an appropriate

    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
    ukas
    -0.08
     keham
    -0.07
    lish
    -0.07
    ehme
    -0.07
    _ERRORS
    -0.07
    æīĢæıIJä¾Ľ
    -0.07
    orthy
    -0.07
    _stuff
    -0.07
    æıIJä¾ĽåIJĦç§į
    -0.07
    umbu
    -0.07
    POSITIVE LOGITS
    .Accept
    0.07
    -match
    0.07
    ä¸İ被åijĬ
    0.07
    ستÙĨ
    0.07
    .match
    0.06
    icode
    0.06
     accept
    0.06
    ÏĢÏī
    0.06
    讳
    0.06
    é¢ĺå¹²
    0.06
    Activations Density 0.008%

    No Known Activations