© 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. 2719
    Prev
    Next
    INDEX
    Explanations

    answer choices

    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
    /dat
    -0.06
    az
    -0.06
    æ¥Ķ
    -0.06
     Dat
    -0.06
    au
    -0.05
    #
    -0.05
    æįŀ
    -0.05
    çĶ±æĿ¥
    -0.05
    åĴĮè°IJ
    -0.05
    iland
    -0.05
    POSITIVE LOGITS
    ACK
    0.08
    æĥŁä¸Ģ
    0.08
    ABCDEFGHIJKLMNOP
    0.08
    ³
    0.08
    piegel
    0.08
    LEASE
    0.08
    بخ
    0.07
    entif
    0.07
    ’a
    0.07
    天ä»Ļ
    0.07
    Activations Density 0.013%

    No Known Activations