© 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. 3989
    Prev
    Next
    INDEX
    Explanations

    boundary condition

    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
     vault
    -0.08
     eldest
    -0.07
     lineage
    -0.07
    æĿ¡æĿ¡
    -0.07
    äºļçī¹
    -0.07
    产åĵģåı¬åĽŀ
    -0.07
    åĿĤ
    -0.07
    ãĥĥãĤ¸
    -0.07
    иÑĤелÑĮÑģÑĤво
    -0.07
     lenght
    -0.06
    POSITIVE LOGITS
     air
    0.09
    fcn
    0.09
    空æ°Ķ
    0.08
    ç½ļ
    0.08
    ffi
    0.08
    _air
    0.08
    åŀ¢
    0.07
    -air
    0.07
     interface
    0.07
    åµIJ
    0.07
    Activations Density 0.003%

    No Known Activations