© 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. 46594
    Prev
    Next
    INDEX
    Explanations

    quantization and units

    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
    ä¸Ģ大åłĨ
    -0.08
     digs
    -0.08
    RequestMethod
    -0.08
    äv
    -0.08
    isca
    -0.07
    åľ°çIJĨä½įç½®
    -0.07
    -condition
    -0.07
    rä
    -0.07
    -pills
    -0.07
     gettimeofday
    -0.07
    POSITIVE LOGITS
     multiples
    0.10
     unit
    0.08
    为åįķä½į
    0.08
     Unit
    0.07
    åĢ¼æĺ¯
    0.07
     celo
    0.07
     units
    0.07
     increments
    0.07
    åłĤ课
    0.07
     unity
    0.07
    Activations Density 0.006%

    No Known Activations