© 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. 9862
    Prev
    Next
    INDEX
    Explanations

    its/their followed by related concepts

    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
    uvi
    -0.08
    å®ŀä½ĵ
    -0.08
    aire
    -0.08
    _compat
    -0.07
    çļĦæĺ¯
    -0.07
     puss
    -0.07
    icker
    -0.07
    åIJĪä½ľåħ±èµ¢
    -0.07
    asten
    -0.07
     Gér
    -0.07
    POSITIVE LOGITS
     surroundings
    0.10
     environs
    0.09
     subsequent
    0.09
     ilk
    0.08
    è¡į
    0.08
     associated
    0.08
    åij¨è¾¹çļĦ
    0.08
    åij¨åĽ´çݯå¢ĥ
    0.07
    åij¨è¾º
    0.07
     surrounding
    0.07
    Activations Density 0.109%

    No Known Activations