© 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. 30716
    Prev
    Next
    INDEX
    Explanations

    possessive noun followed by a noun

    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
    ah
    -0.07
    ohlen
    -0.07
    .mix
    -0.06
    éĵºå¤©çĽĸ
    -0.06
    åIJ¦
    -0.06
    ìĨį
    -0.06
     bump
    -0.06
    åĴ¸
    -0.06
    flug
    -0.06
    åĮĸ
    -0.06
    POSITIVE LOGITS
    аÑĨии
    0.08
    æĥħçļĦ
    0.08
    adal
    0.08
    ×Ĺק
    0.07
    ople
    0.07
    (er
    0.07
    éĩįçĶŁä¹ĭ
    0.07
    áĢ²
    0.07
    áŁĭ
    0.07
    ancode
    0.07
    Activations Density 0.558%

    No Known Activations