© 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. 31983
    Prev
    Next
    INDEX
    Explanations

    testing and solutions

    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
    LY
    -0.07
    hausen
    -0.07
    .addClass
    -0.07
    æŧ
    -0.06
    شا
    -0.06
    伺
    -0.06
    ç¦Ģ
    -0.06
    lement
    -0.06
    讲åı°
    -0.06
    اع
    -0.06
    POSITIVE LOGITS
    refix
    0.08
    åĸľæĢĴåĵĢ
    0.08
     scenarios
    0.08
    )test
    0.07
    éĥ½è§īå¾Ĺ
    0.07
     scenari
    0.07
    å¿ľ
    0.07
    _hdl
    0.07
    aar
    0.07
    ãĥ³ãĥĹ
    0.07
    Activations Density 0.001%

    No Known Activations