© 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. 24490
    Prev
    Next
    INDEX
    Explanations

    "yet" followed by an adjective

    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
    ation
    -0.13
    shire
    -0.10
    ness
    -0.09
    ized
    -0.09
    æĸ°åĬłåĿ¡
    -0.08
    ucho
    -0.08
    ±
    -0.08
    ÙĪÙĬتر
    -0.07
    Ñı
    -0.07
    swick
    -0.07
    POSITIVE LOGITS
    çŁ¥çļĦ
    0.11
    ppure
    0.11
     demikian
    0.09
    enticate
    0.09
    ronic
    0.09
    /OR
    0.09
    à¹Ī
    0.08
    leccion
    0.08
    aning
    0.08
    åĬ©äºİ
    0.08
    Activations Density 0.001%

    No Known Activations