© 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. 22262
    Prev
    Next
    INDEX
    Explanations

    geometric decomposition or splitting

    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
    迹
    -0.07
    èħ¥
    -0.07
     trace
    -0.07
     community
    -0.07
    ลาย
    -0.06
    çį
    -0.06
    ç«ĻåĨħ
    -0.06
    oot
    -0.06
    é¢Ħ示
    -0.06
    æİĴåIJį
    -0.06
    POSITIVE LOGITS
    åĩij
    0.09
    åĪĨ解
    0.08
     decomposition
    0.08
     Decom
    0.08
    çķĻæĥħ
    0.08
     Ñĥк
    0.08
    uny
    0.07
    zept
    0.07
     Chunk
    0.07
    chunk
    0.07
    Activations Density 0.008%

    No Known Activations