© 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. 49110
    Prev
    Next
    INDEX
    Explanations

    explains something works

    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
     this
    -0.12
     thereof
    -0.12
    è¿Ļä¸ĢåĪ»
    -0.11
     therein
    -0.11
    this
    -0.10
     Ùĩذا
    -0.10
     ÑįÑĤоÑĤ
    -0.10
     nÃły
    -0.10
    _this
    -0.10
    è¿Ļ个è¯Ŀé¢ĺ
    -0.10
    POSITIVE LOGITS
    为ä»Ģä¹Īåij¢
    0.09
     happening
    0.09
    itek
    0.08
     banget
    0.07
    done
    0.07
     ÙĥÙĦÙĩ
    0.07
     done
    0.07
    ×Ļר×ķ
    0.07
    åıijçĶŁåľ¨
    0.07
     باÙĦطبع
    0.07
    Activations Density 0.297%

    No Known Activations