© 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. 15160
    Prev
    Next
    INDEX
    Explanations

    code reference or variable declarations

    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
    resso
    -0.08
    ë¦Ħ
    -0.08
    对ä¸Ĭè¿°
    -0.08
    enhagen
    -0.08
    orida
    -0.07
    -ok
    -0.07
    ÑĢаÑĤа
    -0.07
    nock
    -0.07
    åľ¨è¿Ļ次
    -0.07
    ulai
    -0.07
    POSITIVE LOGITS
    å¦Ĥæŀľä¸Ģ个
    0.07
     itself
    0.07
    ä»İä¸Ģ个
    0.07
     indeed
    0.07
     Dé
    0.06
    ãģ«éĻIJ
    0.06
     infatti
    0.06
    å°Ĩä¸Ģ个
    0.06
    dé
    0.06
    æµ·éĩı
    0.06
    Activations Density 0.005%

    No Known Activations