© 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. 41659
    Prev
    Next
    INDEX
    Explanations

    matrix entries

    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
    ħ
    -0.07
     naked
    -0.07
    åijĪçİ°åĩº
    -0.07
    uÄĩ
    -0.06
    諦
    -0.06
    chow
    -0.06
     seco
    -0.06
    Natur
    -0.06
    oros
    -0.06
    à®Łà®¿
    -0.06
    POSITIVE LOGITS
    ä¿
    0.08
    aste
    0.07
     identity
    0.07
    .identity
    0.07
    identity
    0.07
    æĩĴå¾Ĺ
    0.07
    身åĪĨ
    0.07
    Identity
    0.07
     Identity
    0.06
    Äįek
    0.06
    Activations Density 0.009%

    No Known Activations