© 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. 50200
    Prev
    Next
    INDEX
    Explanations

    numbers and text snippets

    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
    æĥľ
    -0.09
    eteg
    -0.08
    ebet
    -0.08
    ruÄį
    -0.07
    å®ĺåºľ
    -0.07
    ÄĻp
    -0.07
    icense
    -0.07
    ffin
    -0.07
    бÑĢе
    -0.07
    ÙĤس
    -0.07
    POSITIVE LOGITS
    ahi
    0.07
    ared
    0.06
    urre
    0.06
    dera
    0.06
     lần
    0.06
    taine
    0.06
    æĹŃæĹ¥
    0.06
    wd
    0.06
    åı·
    0.05
    Sq
    0.05
    Activations Density 0.089%

    No Known Activations