© 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. 1841
    Prev
    Next
    INDEX
    Explanations

    on behalf of

    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
    odel
    -0.07
    icité
    -0.07
    raga
    -0.07
    irut
    -0.07
    ition
    -0.07
    /providers
    -0.07
    åIJĮå¿Ĺ们
    -0.07
     createContext
    -0.06
    æĹ¥çĶŁ
    -0.06
    管äºĭ
    -0.06
    POSITIVE LOGITS
     behalf
    0.14
    代表
    0.10
    代è¨Ģ
    0.10
    代人
    0.10
    代为
    0.10
     mewakili
    0.09
    代
    0.09
    ä»ħ代表
    0.09
    åıªä»£è¡¨
    0.09
    æĽ¿
    0.08
    Activations Density 0.348%

    No Known Activations