© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17072
    Prev
    Next
    INDEX
    Explanations

    configuration options

    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
    åIJ¾å°Ķ
    -0.08
    /il
    -0.08
     пеÑĢего
    -0.07
    erder
    -0.07
    [action
    -0.07
    ukum
    -0.07
    å®ĭè¯į
    -0.07
     Skyl
    -0.07
    uko
    -0.07
    vard
    -0.07
    POSITIVE LOGITS
    ocha
    0.07
    hiro
    0.07
     van
    0.07
    ÙĨس
    0.06
    纤
    0.06
    unch
    0.06
    ä¹ĭæľ¬
    0.06
    umper
    0.06
    æķĽ
    0.06
    oly
    0.06
    Activations Density 0.001%

    No Known Activations