© 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. 14658
    Prev
    Next
    INDEX
    Explanations

    electronic computing platforms

    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
    ä¼Ĺ
    -0.07
    aval
    -0.07
     slu
    -0.07
    LING
    -0.07
    FromClass
    -0.07
    estro
    -0.06
    lings
    -0.06
    گرÛĮ
    -0.06
    lian
    -0.06
    gether
    -0.06
    POSITIVE LOGITS
    åįĥæĸ¹
    0.07
    俱ä¹IJéĥ¨
    0.07
    agu
    0.07
    å«Į
    0.07
    _FORE
    0.07
    è¨Ī
    0.07
    uche
    0.07
    æŀģ管
    0.07
    zyn
    0.06
    <location
    0.06
    Activations Density 0.002%

    No Known Activations