© 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. 49484
    Prev
    Next
    INDEX
    Explanations

    technical noun endings

    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
     Heller
    -0.07
    untime
    -0.07
     zufolge
    -0.07
    να
    -0.07
    ç®Ĺæĺ¯
    -0.07
    -needed
    -0.07
     Äijằng
    -0.06
    æĢª
    -0.06
    γι
    -0.06
    -strokes
    -0.06
    POSITIVE LOGITS
    çļĦåIJĦ项
    0.07
    å¦Ĥæŀľèĥ½å¤Ł
    0.07
    踩çĿĢ
    0.07
    Ùĥب
    0.07
    ehme
    0.07
    advert
    0.06
    åıĬéĻĦåĬł
    0.06
    该åIJį
    0.06
    _FM
    0.06
    adera
    0.06
    Activations Density 0.108%

    No Known Activations