© 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. 19267
    Prev
    Next
    INDEX
    Explanations

    delegation and referral

    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
    kse
    -0.07
    æĽ´æĸ°æĹ¥æľŁ
    -0.07
    à¸ŀย
    -0.07
    باÙĨ
    -0.07
    dsl
    -0.06
    å°±ä½į
    -0.06
    è¦ģç´§
    -0.06
    Canceled
    -0.06
    ÑĪÑĤо
    -0.06
    æĮĩ导åijĺ
    -0.06
    POSITIVE LOGITS
    交ç»Ļ
    0.11
    å§Ķæīĺ
    0.11
    交ç»ĻäºĨ
    0.11
    交給
    0.10
    ä»»ãģĽ
    0.10
    交çĶ±
    0.10
     delegation
    0.10
     deleg
    0.09
    转åĪ°
    0.09
     Delegate
    0.09
    Activations Density 0.170%

    No Known Activations