© 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. 17840
    Prev
    Next
    INDEX
    Explanations

    mathematical variables and symbols

    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
    amel
    -0.08
     dis
    -0.06
    á»ĩt
    -0.06
    å¾ħ
    -0.06
     '');
    -0.06
     critically
    -0.05
    hi
    -0.05
    èIJ½èIJ½
    -0.05
     tod
    -0.05
     tand
    -0.05
    POSITIVE LOGITS
    éĻ¤äºĨæľī
    0.09
    isien
    0.08
    åĴĮåĪĺ
    0.08
    atica
    0.08
    /slick
    0.08
    caler
    0.08
    plice
    0.08
     Sputnik
    0.07
    æĬĬä»ĸçļĦ
    0.07
    æĸ°ä¸Ģå±Ĭ
    0.07
    Activations Density 0.010%

    No Known Activations