© 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. 19054
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    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
    åīįèĢħ
    -0.08
    uert
    -0.08
    à¤Ĥà¤Ł
    -0.08
     berdua
    -0.08
    æľī家
    -0.07
    ละ
    -0.07
    TestFixture
    -0.07
    untu
    -0.07
    endr
    -0.07
    ^K
    -0.07
    POSITIVE LOGITS
    è¿Ļä¸ī个
    0.10
    è¿Ļä¸ī
    0.08
    è¿Ļä¸īç§į
    0.08
    ä¸ī个
    0.08
    three
    0.08
    ä¸ī项
    0.07
    ä¸īèĢħ
    0.07
    ä¸īä½į
    0.07
    ä¸īæĸ¹
    0.07
     triplet
    0.07
    Activations Density 0.084%

    No Known Activations