© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 9312
    Prev
    Next
    INDEX
    Explanations

    proper nouns followed by descriptions

    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
    erts
    -0.08
    麻
    -0.07
    å¹¿æ³Ľå¼Ģå±ķ
    -0.07
    صÙģ
    -0.07
    rans
    -0.07
    çľĭçĿĢæĪij
    -0.06
    éĩijé¾Ļ
    -0.06
    ért
    -0.06
    åħ°çī¹
    -0.06
    èŁĴ
    -0.06
    POSITIVE LOGITS
    EventListener
    0.07
    essim
    0.07
    Occurred
    0.07
    ivu
    0.06
    å§ĭèĩ³
    0.06
    èĢģåİ»
    0.06
    Authenticated
    0.06
    tivo
    0.06
    å®ĪåĢĻ
    0.06
    åįģäºĮç«ł
    0.06
    Activations Density 0.003%

    No Known Activations