© 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. 65067
    Prev
    Next
    INDEX
    Explanations

    infinitive to

    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
    年建
    -0.08
    aldi
    -0.07
    cios
    -0.07
    waltungs
    -0.07
    ubl
    -0.07
    ì°°
    -0.07
    ×ķ׳×Ļ×Ŀ
    -0.07
    omic
    -0.07
    omme
    -0.07
    ChangedEventArgs
    -0.07
    POSITIVE LOGITS
    /todo
    0.07
    ottie
    0.07
    ä¸ºåĽ½
    0.06
    ç«ŀ
    0.06
    åĪļ
    0.06
    wege
    0.06
    ipple
    0.06
    äºĮè¦ģ
    0.06
    ä¹ħ
    0.06
    unger
    0.06
    Activations Density 0.010%

    No Known Activations