© 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. 32010
    Prev
    Next
    INDEX
    Explanations

    known values with calibration or reference

    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
    ipel
    -0.07
    ä¹IJä¹İ
    -0.07
     toward
    -0.07
    laki
    -0.07
    èĨ
    -0.07
    åIJİ继
    -0.06
    åĭŁ
    -0.06
    çŃĸ
    -0.06
    æĴŃç§į
    -0.06
    éĢļå¾Ģ
    -0.06
    POSITIVE LOGITS
     known
    0.10
    known
    0.10
     Known
    0.10
    _known
    0.10
    æł¡
    0.09
    Benchmark
    0.09
    -known
    0.09
    Known
    0.09
    testdata
    0.09
     Benchmark
    0.09
    Activations Density 0.195%

    No Known Activations