© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 43776
    Prev
    Next
    INDEX
    Explanations

    two, double, twice, tandem, pair

    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
    èī²åĪĹ
    -0.11
    енÑĮ
    -0.09
    anson
    -0.09
    /pm
    -0.08
    issima
    -0.08
    ingers
    -0.08
    edik
    -0.08
    erg
    -0.08
    ازÙĦ
    -0.08
    lair
    -0.08
    POSITIVE LOGITS
    æĺ¯ä¸¤ä¸ª
    0.09
     tandem
    0.08
    æĪĸå¤ļ
    0.08
    èĥĮéĿł
    0.07
    (Double
    0.07
    两个
    0.07
     TWO
    0.07
    nd
    0.07
    åıĬ以ä¸Ĭ
    0.07
     Two
    0.07
    Activations Density 0.099%

    No Known Activations