© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21936
    Prev
    Next
    INDEX
    Explanations

    superconducting transition temperature T<sub>c</sub>

    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
    ä½İåIJ¸
    -0.07
    orro
    -0.07
    arre
    -0.07
     amator
    -0.07
    auce
    -0.07
    æľªå°½
    -0.07
    mania
    -0.06
    åıĮ缮
    -0.06
    èIJ½èIJ½
    -0.06
    anio
    -0.06
    POSITIVE LOGITS
    %E
    0.08
     Fucking
    0.07
    วà¸ļ
    0.07
    à¹Īวà¸ĩ
    0.07
    çļĦæľīåħ³
    0.07
    è¿ĻäºĽä¸ľè¥¿
    0.07
    äºĨ大éĩıçļĦ
    0.07
    管çIJĨç±»
    0.06
    ?...
    0.06
    åŁºçŁ³
    0.06
    Activations Density 0.022%

    No Known Activations