© 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. 26494
    Prev
    Next
    INDEX
    Explanations

    names of people, places, or technical terms

    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
    äºİä¸Ģä½ĵçļĦ
    -0.06
    ä¸ľè¥¿
    -0.06
    è¿°
    -0.06
    说æĸĩ
    -0.06
    è¦ģæ±Ĥåľ¨
    -0.06
    æ¦Ĥè¿°
    -0.06
    ÙĦاء
    -0.06
     smoother
    -0.06
    å¿ħé¡»åľ¨
    -0.06
    Ñģловно
    -0.06
    POSITIVE LOGITS
    quential
    0.08
    ï¼Ŀï¼Ŀï¼Ŀï¼Ŀ
    0.08
    ynos
    0.07
    æĤ¨çļĦè¯Ħ论
    0.07
    éĩĮäºļ
    0.07
    社
    0.07
    estatus
    0.07
    ztat
    0.07
    oura
    0.07
    USTA
    0.07
    Activations Density 0.010%

    No Known Activations