© 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. 31641
    Prev
    Next
    INDEX
    Explanations

    WK-League

    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
    åĪĨéĴŁåīį
    -0.07
    oment
    -0.07
    AGER
    -0.07
    ulare
    -0.07
    coni
    -0.07
     MERCHANTABILITY
    -0.07
     اÙĦ
    -0.07
    Compr
    -0.07
    诽
    -0.07
    OUNDS
    -0.07
    POSITIVE LOGITS
    æŃ£ä¸Ń
    0.07
    âĢ¦the
    0.07
    verk
    0.07
    aka
    0.07
    êt
    0.06
    ...]
    0.06
    åĪĨæĺİ
    0.06
    âĢ¦*
    0.06
    etsk
    0.06
    itional
    0.06
    Activations Density 0.287%

    No Known Activations