© 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. 58006
    Prev
    Next
    INDEX
    Explanations

    linear combination of functions

    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
    issy
    -0.07
    án
    -0.07
     commend
    -0.07
    å¾·æĸ¯
    -0.06
    ønd
    -0.06
    quÃŃ
    -0.06
    tida
    -0.06
    çļĦ人éĻħåħ³ç³»
    -0.06
    ipher
    -0.06
    æĹº
    -0.06
    POSITIVE LOGITS
    basis
    0.08
    iras
    0.08
     linear
    0.08
    uyến
    0.08
     Linear
    0.08
     exponential
    0.07
    VML
    0.07
     Fired
    0.07
    线æĢ§
    0.07
    linear
    0.07
    Activations Density 0.014%

    No Known Activations