© 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. 47643
    Prev
    Next
    INDEX
    Explanations

    MySQL SQL database

    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
    åıįè¿ĩæĿ¥
    -0.08
    گر
    -0.07
    åĽŀ溯
    -0.07
    .SC
    -0.07
    çĪ¬
    -0.07
    æĪ»
    -0.07
     ulang
    -0.07
    anto
    -0.07
     resurgence
    -0.07
    ÐĿÐļ
    -0.07
    POSITIVE LOGITS
    åİŁæľīçļĦ
    0.10
    åİŁæľī
    0.10
    ä½ĨéļıçĿĢ
    0.10
    åİŁæĺ¯
    0.09
    åİŁæľ¬æĺ¯
    0.09
    à¹Ģà¸Ķิม
    0.09
     original
    0.09
     originally
    0.08
    åİŁæľ¬çļĦ
    0.08
     baseline
    0.08
    Activations Density 0.199%

    No Known Activations