© 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. 33951
    Prev
    Next
    INDEX
    Explanations

    preposition 'in'

    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
    allis
    -0.07
    ç¡®å®ļ为
    -0.07
    ª½
    -0.07
    аÑģа
    -0.07
    asco
    -0.07
    ë¡ľìĦľ
    -0.07
    (fil
    -0.06
    esten
    -0.06
    è¿ĩ好
    -0.06
    好åIJ§
    -0.06
    POSITIVE LOGITS
    verts
    0.08
    */)
    0.07
     */)
    0.07
    oned
    0.07
     Bá
    0.07
     presentes
    0.07
    ierer
    0.07
    anteil
    0.06
    à¸Ļีà¹īà¸Īะ
    0.06
    woke
    0.06
    Activations Density 0.258%

    No Known Activations