© 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. 56246
    Prev
    Next
    INDEX
    Explanations

    confirmation or emphasis ("right", "yep", "yup")

    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
    åıįåĢĴæĺ¯
    -0.08
    umno
    -0.08
    Ùĩ
    -0.08
    <|box_end|>
    -0.08
    oader
    -0.08
    ieza
    -0.08
    åħ®åħ®
    -0.08
    tika
    -0.08
    åį´è¿ĺæĺ¯
    -0.08
    失æݪ
    -0.07
    POSITIVE LOGITS
    /*!
    0.07
    oretical
    0.07
    oret
    0.06
    chi
    0.06
    oug
    0.06
    æľīæѤ
    0.06
    ing
    0.06
    une
    0.06
     Heavenly
    0.06
    å¦ŀ
    0.06
    Activations Density 0.006%

    No Known Activations