© 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. 17338
    Prev
    Next
    INDEX
    Explanations

    San Francisco

    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
    å¤ļè°¢
    -0.07
    zwi
    -0.06
     distraction
    -0.06
    ми
    -0.06
    ç§ijçļĦ
    -0.06
    ondi
    -0.06
    鬣
    -0.06
    æ»´æ°´
    -0.06
    çģ«çĥ§
    -0.06
    æģĥ
    -0.06
    POSITIVE LOGITS
    ä»»åĬ³
    0.07
    âķIJâķIJâķIJâķIJ
    0.07
    ennie
    0.07
    åĽ½å®¶è§Ħå®ļ
    0.07
    mailer
    0.07
    ä»»æĢ¨
    0.07
    acer
    0.07
    æ®ĸ
    0.07
    zheimer
    0.06
    Bezier
    0.06
    Activations Density 0.539%

    No Known Activations