© 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. 23813
    Prev
    Next
    INDEX
    Explanations

    possessive noun followed by noun

    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
    ert
    -0.08
     \"{
    -0.07
    erti
    -0.07
    ycl
    -0.07
    å¦Ĥæŀľè§īå¾Ĺ
    -0.07
    nette
    -0.07
    å¾ħå®ļ
    -0.07
    ema
    -0.07
    awaiter
    -0.07
     lorem
    -0.07
    POSITIVE LOGITS
    Âł
    0.09
    ³³³
    0.08
    ³³
    0.08
    ³³³³
    0.08
    ³³³³³³³³
    0.07
    ³³³³³³³
    0.07
     saj
    0.06
    Ä°L
    0.06
    ayani
    0.06
    纪
    0.06
    Activations Density 6.206%

    No Known Activations