© 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. 14597
    Prev
    Next
    INDEX
    Explanations

    classification or type

    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
    ãĥ«ãĥī
    -0.09
    بار
    -0.08
    aÅŁ
    -0.07
    anh
    -0.07
    æĪĸå°ij
    -0.07
    ilter
    -0.07
    ÙĦاÙĤ
    -0.07
    åѦéĩij
    -0.07
    inking
    -0.07
    umbed
    -0.07
    POSITIVE LOGITS
    åĴĮå·¥ä½ľ
    0.07
    /method
    0.07
    ãģĽãģ¦
    0.07
    åĴĮæĶ¿çŃĸ
    0.07
    åĴĮåĨħ容
    0.07
    åĴĮçłĶ究
    0.07
    åĴĮæĸ¹æ³ķ
    0.06
    åĴĮæķ°æį®
    0.06
    /function
    0.06
    åĴĮ管çIJĨ
    0.06
    Activations Density 0.264%

    No Known Activations