© 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. 12702
    Prev
    Next
    INDEX
    Explanations

    code delimiters or comments

    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
    erti
    -0.09
    apan
    -0.08
    odox
    -0.08
    ((&
    -0.07
    ipan
    -0.07
    {/*
    -0.07
    åĸ«èĮ¶
    -0.07
    erten
    -0.07
    _php
    -0.07
    еÑĢа
    -0.07
    POSITIVE LOGITS
    0.07
    ãĢģ
    0.06
    ""
    0.06
    oute
    0.06
    mutations
    0.06
    >>
    0.05
    åĪ©åĻ¨
    0.05
    æ¿
    0.05
     Tan
    0.05
    CP
    0.05
    Activations Density 0.137%

    No Known Activations