© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 9474
    Prev
    Next
    INDEX
    Explanations

    expressions like `2y\frac{dy}{dx}-\frac{dy}{dx}`, `b(d-c) < a(d-c)`, `(x+7)^2`, `**`, `-3*j**5`.mathematical and code expressions

    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
    å°»
    -0.07
    æķ£çļĦ
    -0.07
    æķ£
    -0.07
    ç»İ
    -0.06
    ulum
    -0.06
    æĮĩæķĻ
    -0.06
    éĻĢ
    -0.06
    ãģķãģĦ
    -0.06
    ç͍æĿ¥
    -0.06
     Lines
    -0.06
    POSITIVE LOGITS
    oftware
    0.08
     Howard
    0.07
    aja
    0.07
    pell
    0.07
    achie
    0.07
    epad
    0.07
    umeric
    0.07
    åĪĢåĪĥ
    0.07
    .spacing
    0.07
    åIJĦè¡Į
    0.07
    Activations Density 0.002%

    No Known Activations