© 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. 55417
    Prev
    Next
    INDEX
    Explanations

    professional roles and initiatives

    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
    èĩªå·±è¢«
    -0.08
    æIJŃä¸Ĭ
    -0.07
    æĸĩåĮĸä¸Ń
    -0.07
    Manufacturer
    -0.07
    åį«çĶŁä¹łæĥ¯
    -0.06
    yce
    -0.06
     thu
    -0.06
    åıªä¸įè¿ĩ
    -0.06
    æ¥ŃèĢħ
    -0.06
    çīŁå°¼
    -0.06
    POSITIVE LOGITS
    ï¼Ĩ
    0.09
     degusta
    0.08
    &
    0.08
    并ç»Ħç»ĩ
    0.08
     division
    0.08
    çıĪ
    0.08
    division
    0.08
     affairs
    0.08
    产åĵģä¸Ńå¿ĥ
    0.08
    ä¸İåıijå±ķ
    0.07
    Activations Density 0.539%

    No Known Activations