© 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. 40146
    Prev
    Next
    INDEX
    Explanations

    code implementation

    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
     Flake
    -0.07
    rix
    -0.07
    iski
    -0.07
    æĤłæī¬
    -0.07
    RIX
    -0.07
    UG
    -0.06
    ä¸ĭåİ»
    -0.06
    ĸ
    -0.06
    ë£Į
    -0.06
    à¸Ļิ
    -0.06
    POSITIVE LOGITS
    ensus
    0.08
    .INPUT
    0.08
     ÐĴÑģÑĤÑĢе
    0.07
    .yahoo
    0.07
    æĪĺ
    0.07
    ÅĽci
    0.07
    dio
    0.07
    eder
    0.07
    anta
    0.07
    ña
    0.07
    Activations Density 0.001%

    No Known Activations