© 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. 57434
    Prev
    Next
    INDEX
    Explanations

    programmer syntax

    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
    heds
    -0.08
    ILLE
    -0.07
    osi
    -0.07
    jun
    -0.07
    ille
    -0.07
    åIJijæĿ¥
    -0.07
    æĭĦ
    -0.06
    æĿİäºij
    -0.06
    ubb
    -0.06
    æĬ¥åijĬ书
    -0.06
    POSITIVE LOGITS
    ãĥģãĥ©
    0.08
    ãĥ«ãĤ¯
    0.08
    irim
    0.07
    igi
    0.07
     Spicer
    0.07
     Britt
    0.07
    好åķĬ
    0.07
    verstanden
    0.07
    UCT
    0.07
     chatt
    0.07
    Activations Density 0.024%

    No Known Activations