© 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. 11005
    Prev
    Next
    INDEX
    Explanations

    This/these followed by a description

    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
    zze
    -0.08
    æĮģ
    -0.08
    äºĶæĺ¯
    -0.07
    èĪ¬
    -0.07
    lius
    -0.07
    åıįèĢĮä¼ļ
    -0.07
    usu
    -0.07
    ÑĢое
    -0.07
    kar
    -0.07
    å¾ħç»Ń
    -0.07
    POSITIVE LOGITS
    åºĶå½ĵä¾Ŀçħ§
    0.06
    ä¹ĭæīĢ以
    0.06
    oret
    0.06
     Aman
    0.06
     includes
    0.06
     essentially
    0.06
    ':{'
    0.06
    æŀĿ头
    0.06
    åIJįæĢĿ
    0.06
    è£ķ
    0.06
    Activations Density 0.092%

    No Known Activations