© 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. 31307
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers and code

    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
    oha
    -0.06
    à¹Ģà¸ĭล
    -0.06
    IGA
    -0.06
    kens
    -0.06
    lapping
    -0.06
    odem
    -0.06
    ilon
    -0.06
    alani
    -0.06
    ayan
    -0.06
     ↵
    -0.06
    POSITIVE LOGITS
    åĬłåħ¥æĶ¶èĹı
    0.08
    PPER
    0.08
     Cald
    0.08
    æİĴåIJįåīį
    0.08
    第ä¹Ŀå±Ĭ
    0.08
     Chronicle
    0.07
    rž
    0.07
    pios
    0.07
    _evt
    0.07
    äºĶæĺŁ
    0.07
    Activations Density 0.010%

    No Known Activations