© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14165
    Prev
    Next
    INDEX
    Explanations

    multiple choice options

    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
    ç¬ĭ
    -0.07
    足çļĦ
    -0.06
    åĪĢ
    -0.06
     rec
    -0.06
    æ¸ħçļĦ
    -0.06
    otime
    -0.06
    åIJĦè¡ĮåIJĦä¸ļ
    -0.06
    åĪĢçļĦ
    -0.06
    ubar
    -0.06
    çĽĸ
    -0.06
    POSITIVE LOGITS
    èIJĿèİī
    0.08
    æݲ
    0.08
     Cra
    0.07
    omis
    0.07
    åľĸåĥı
    0.07
    <img
    0.07
    åħĪåĪ°åħĪå¾Ĺ
    0.07
    chon
    0.07
    ukes
    0.07
    าà¸ĩ
    0.07
    Activations Density 0.018%

    No Known Activations