© 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. 32328
    Prev
    Next
    INDEX
    Explanations

    signal receptions

    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
    heb
    -0.07
    Indented
    -0.07
    ä½łå¥½
    -0.07
    飶
    -0.07
    leck
    -0.07
     Somm
    -0.07
    åįĹ宫
    -0.07
    éļĨ
    -0.07
    ìĬµ
    -0.06
    /function
    -0.06
    POSITIVE LOGITS
    身åıĹ
    0.08
    å®ĥ们çļĦ
    0.07
    è¿Ļè¾¹çļĦ
    0.07
     councils
    0.07
    getc
    0.07
    кÑĥлÑĮ
    0.07
    æĪijä¹Łæľī
    0.07
    ÙĪدÙĬ
    0.06
    å¼Ĥ彩
    0.06
    _pull
    0.06
    Activations Density 0.104%

    No Known Activations