© 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. 33228
    Prev
    Next
    INDEX
    Explanations

    resolved ties

    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
    ovia
    -0.07
    idel
    -0.07
    amet
    -0.07
    ä¸Ģçݯ
    -0.07
    ÏĦÏģο
    -0.06
    åħ¨æĸĩéĺħ读
    -0.06
    rup
    -0.06
    UnderTest
    -0.06
    .proc
    -0.06
    menn
    -0.06
    POSITIVE LOGITS
    ĥĿ
    0.08
    æĢİä¹ĪåĬŀ
    0.08
    åıijçĶŁæŶ
    0.08
    sce
    0.08
    ä¸įåĨ³
    0.08
    äºī
    0.08
    kinson
    0.07
    éĢīæĭ©ä¸įåIJĮçļĦ
    0.07
    ients
    0.07
    æĥħåĨµä¸ĭ
    0.07
    Activations Density 0.008%

    No Known Activations