© 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. 40982
    Prev
    Next
    INDEX
    Explanations

    home and house

    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
    è§Ĥåħī
    -0.08
    å¹¿åľº
    -0.07
    ãĥ¬ãĥ³ãĤ¿
    -0.07
    å»£åł´
    -0.07
    ä¹ĭè¾Ī
    -0.07
    йÑģ
    -0.07
    æ±łä¸Ń
    -0.07
    人群ä¸Ń
    -0.07
    è¿IJåĬĽ
    -0.06
    åIJĦ大
    -0.06
    POSITIVE LOGITS
    /home
    0.10
    温馨
    0.10
     premises
    0.10
     home
    0.10
     house
    0.10
    温馨çļĦ
    0.10
    ä½ıå®ħ
    0.09
    (home
    0.09
    home
    0.09
     domic
    0.09
    Activations Density 0.601%

    No Known Activations