© 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. 63751
    Prev
    Next
    INDEX
    Explanations

    falseč / trueč sequences

    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
    lify
    -0.09
     \''
    -0.08
     sufrir
    -0.08
    flix
    -0.08
    èĮģ
    -0.08
    usura
    -0.08
    zilla
    -0.08
    ä¸ĩåħ¬éĩĮ
    -0.08
    -dismissible
    -0.07
    beauf
    -0.07
    POSITIVE LOGITS
    æľīè¯Ŀ
    0.07
     unk
    0.06
    ÙĨج
    0.06
    oracle
    0.06
     Incident
    0.06
     ach
    0.06
    æĿĤ
    0.06
    Boost
    0.06
    åıĭ
    0.06
    ç±į
    0.05
    Activations Density 0.008%

    No Known Activations