© 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. 11927
    Prev
    Next
    INDEX
    Explanations

    code structure attributes

    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
    åĨ·åĵ¼
    -0.07
    ç¼Ī
    -0.07
    vertis
    -0.07
    kot
    -0.07
    okol
    -0.07
    æ°ĶåĢĻåıĺåĮĸ
    -0.06
     Sod
    -0.06
    .React
    -0.06
     "&#
    -0.06
     angst
    -0.06
    POSITIVE LOGITS
    éĤ¦
    0.07
     Max
    0.07
    åıĤæķ°
    0.07
    defaults
    0.07
    èĸĩèĸĩ
    0.07
    verbosity
    0.07
     parameters
    0.07
    äºĨä¸ĢåĪĩ
    0.07
    maximum
    0.07
    /max
    0.07
    Activations Density 0.533%

    No Known Activations