© 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. 43100
    Prev
    Next
    INDEX
    Explanations

    mathematical functions and notations

    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
    ilah
    -0.07
    éch
    -0.07
    ×¥
    -0.07
     <*>
    -0.07
    ä»Ĭ天çļĦ
    -0.06
    çļĦåIJİ
    -0.06
    ()]
    -0.06
    uten
    -0.06
    émy
    -0.06
    icat
    -0.06
    POSITIVE LOGITS
    渡åģĩ
    0.08
    [color
    0.07
    registre
    0.07
    wol
    0.07
    zieh
    0.07
    åıĬè¦ģæ±Ĥ
    0.07
    éĿĻå¿ĥ
    0.06
    ussia
    0.06
    alue
    0.06
     alot
    0.06
    Activations Density 0.012%

    No Known Activations