© 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. 28681
    Prev
    Next
    INDEX
    Explanations

    prepositions and articles preceding specific nouns

    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
    y
    -0.07
    æŁ
    -0.07
    vg
    -0.07
    Constructor
    -0.06
    Interface
    -0.06
    ante
    -0.06
    ä¸Ģ
    -0.06
    skom
    -0.06
    yne
    -0.06
    åĨįä¹Łä¸į
    -0.06
    POSITIVE LOGITS
    llib
    0.08
    unca
    0.07
    undef
    0.07
    ajem
    0.07
    dbg
    0.07
    quina
    0.07
    åĨµ
    0.07
    )','
    0.07
    दार
    0.07
    lightbox
    0.07
    Activations Density 0.028%

    No Known Activations