© 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. 30776
    Prev
    Next
    INDEX
    Explanations

    slash followed by specific terms

    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
    (er
    -0.07
    éľİ
    -0.07
    egi
    -0.06
    Ù°
    -0.06
    µ
    -0.06
    ÙİØ·
    -0.06
    ICENSE
    -0.06
    es
    -0.06
    æľīåĽĽ
    -0.06
     pula
    -0.06
    POSITIVE LOGITS
    ront
    0.09
    ़
    0.08
    reat
    0.08
    ly
    0.08
    æ³Ĭå°Ķ
    0.08
    sob
    0.08
    ×ķ×Ĺ
    0.08
    aison
    0.08
    rut
    0.08
    สิà¹īà¸Ļ
    0.08
    Activations Density 0.451%

    No Known Activations