© 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. 22283
    Prev
    Next
    INDEX
    Explanations

    programming language keywords and characters

    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
    ı
    -0.06
    à¹Ĩ
    -0.06
     à¹Ĩ
    -0.06
    çIJĽ
    -0.06
    inite
    -0.06
    ½
    -0.05
    ,
    -0.05
    леÑģ
    -0.05
    åħļçļĦ建设
    -0.05
    idae
    -0.05
    POSITIVE LOGITS
     (('
    0.09
    ylum
    0.09
    çĮ¬
    0.08
     ÐIJпÑĢе
    0.08
    ”âĢ¦
    0.08
    arit
    0.08
    çīĪæĿĥå½ĴåİŁä½ľèĢħ
    0.08
    IFF
    0.08
    æld
    0.08
    åħ³äºİåģļ好
    0.08
    Activations Density 0.621%

    No Known Activations