© 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. 26659
    Prev
    Next
    INDEX
    Explanations

    ann, eta, operator

    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
    纬
    -0.08
    åıī
    -0.07
    hire
    -0.07
    ayout
    -0.07
    Occurred
    -0.06
    åľ¨åħ¨å¸Ĥ
    -0.06
    è°ĥæŁ¥æĺ¾ç¤º
    -0.06
     natal
    -0.06
    oy
    -0.06
    Ùĩر
    -0.06
    POSITIVE LOGITS
    cac
    0.08
     Pale
    0.08
    adera
    0.07
    ipa
    0.07
    æĪĺåĮº
    0.07
    Å¡te
    0.07
    eley
    0.07
    agra
    0.07
    umpang
    0.07
    anty
    0.07
    Activations Density 0.004%

    No Known Activations