© 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. 33650
    Prev
    Next
    INDEX
    Explanations

    numbers and periods

    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
    çªĥ
    -0.08
    ttp
    -0.07
    odo
    -0.07
    åĴĮæĬķèµĦ
    -0.06
    uality
    -0.06
    ovy
    -0.06
    .cms
    -0.06
    zicht
    -0.06
    ä¸İæĬķèµĦ
    -0.06
    -m
    -0.06
    POSITIVE LOGITS
    eran
    0.07
    ç»´äºļ
    0.07
    inoa
    0.07
    iraz
    0.07
    ลัà¸ļ
    0.07
    imba
    0.07
    ç»ı
    0.07
    ê¸ī
    0.07
    ç¶ĵ
    0.06
    积æŀģç»Ħç»ĩ
    0.06
    Activations Density 0.021%

    No Known Activations