© 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. 46234
    Prev
    Next
    INDEX
    Explanations

    chemical compounds with subscripts

    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
    æ¯Ľæ³½ä¸ľ
    -0.07
    a
    -0.07
    f
    -0.07
    ellen
    -0.07
    بÙĪ
    -0.06
    æĸ°åĬłåĿ¡
    -0.06
    on
    -0.06
    ement
    -0.06
    0
    -0.06
     Lauf
    -0.06
    POSITIVE LOGITS
     prostituer
    0.08
    åĽĽä¸Ń
    0.08
    èIJ©
    0.08
    ulich
    0.08
    ulia
    0.08
     inizial
    0.08
    gerald
    0.08
    两ä¸į误
    0.07
    ÎŃÏģα
    0.07
    lasses
    0.07
    Activations Density 0.006%

    No Known Activations