© 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. 22269
    Prev
    Next
    INDEX
    Explanations

    $g_{ij}$ is Riemannian metric, $h_{ij}$ is second fundamental form

    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
    èIJ½èIJ½
    -0.07
    ä¹ĭ交
    -0.07
    å°ĬéĩįåĴĮ
    -0.06
    atar
    -0.06
    maf
    -0.06
     пен
    -0.06
    misc
    -0.06
    nom
    -0.06
    .o
    -0.06
     Giảng
    -0.06
    POSITIVE LOGITS
    Ä©
    0.08
    iku
    0.08
    å±Ģ
    0.07
    è±Į
    0.07
    è°±
    0.07
    Matchers
    0.07
    津津
    0.07
    åī¯ç§ĺ书éķ¿
    0.07
    ourcing
    0.07
    νεÏĤ
    0.07
    Activations Density 0.003%

    No Known Activations