© 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. 40046
    Prev
    Next
    INDEX
    Explanations

    to the

    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
    orra
    -0.07
    彪
    -0.07
    ase
    -0.06
    oller
    -0.06
    æŀļ
    -0.06
    ose
    -0.06
     Burr
    -0.06
    çīĽ
    -0.06
    esia
    -0.06
    sei
    -0.06
    POSITIVE LOGITS
    æĢ»ä½ĵä¸Ĭ
    0.08
    æķ´ä½ĵä¸Ĭ
    0.08
    ЧÐĺ
    0.07
    ëł¹
    0.07
    èĦ¸çļĦ
    0.07
    ijľ
    0.07
    æĢ»ä½ĵèĢĮè¨Ģ
    0.07
    ×ķר×ķת
    0.07
    ÙĪØŃØ©
    0.07
    bast
    0.07
    Activations Density 0.289%

    No Known Activations