© 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. 50082
    Prev
    Next
    INDEX
    Explanations

    mathematical and code functions

    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
    ibat
    -0.08
    [".
    -0.07
    itura
    -0.07
    apat
    -0.06
    æĦŁæŁĵèĢħ
    -0.06
    ['__
    -0.06
    Alice
    -0.06
     Hạt
    -0.06
    ìłķ
    -0.06
     proper
    -0.06
    POSITIVE LOGITS
    èµ·
    0.07
     subparagraph
    0.07
    _whitespace
    0.07
    ä¸Ģå®ļçļĦ
    0.07
    ä¸ĸ
    0.07
     [âĢ¦
    0.07
    ä¸Ģå®ļ
    0.06
    ÙĪÙĦØ©
    0.06
    ázÃŃ
    0.06
    åĪĨæĺİ
    0.06
    Activations Density 0.022%

    No Known Activations