© 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. 42175
    Prev
    Next
    INDEX
    Explanations

    gate transistors or components

    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
    nett
    -0.07
    nos
    -0.07
    夸
    -0.07
    ocks
    -0.06
    çĮĸ
    -0.06
    egin
    -0.06
    åĴĮä¸į
    -0.06
    å¢ŀ强ä½ĵè´¨
    -0.06
    ances
    -0.06
     rij
    -0.06
    POSITIVE LOGITS
    -mounted
    0.08
    ypass
    0.07
     ÙħÙĨز
    0.07
    ERIA
    0.07
    _bias
    0.07
    cheap
    0.07
     Malk
    0.07
    CONTROL
    0.07
    ighest
    0.07
    éŀĺ
    0.07
    Activations Density 0.014%

    No Known Activations