© 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. 19009
    Prev
    Next
    INDEX
    Explanations

    equations and numbers

    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
    RELEASE
    -0.07
    ziale
    -0.07
    çĥŃåĪº
    -0.07
    iebe
    -0.07
    ecke
    -0.07
    å·´èIJ¨
    -0.07
    orien
    -0.07
    .persistent
    -0.07
    æĹ¥ãģ«ãģ¯
    -0.07
    ancel
    -0.07
    POSITIVE LOGITS
    åIJĴ
    0.08
    acob
    0.07
    以å¾Į
    0.06
    oon
    0.06
     Jun
    0.06
    aft
    0.06
    以åIJİ
    0.06
    ideo
    0.06
     Junior
    0.06
    æīĵç®Ĺ
    0.06
    Activations Density 0.011%

    No Known Activations