© 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. 34425
    Prev
    Next
    INDEX
    Explanations

    average, Screen charge

    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
    edah
    -0.08
    IfExists
    -0.08
    burgh
    -0.08
    xD
    -0.07
    çĴĥ
    -0.07
    ä¸įåıĬå¾ħ
    -0.07
    alii
    -0.07
    Ī¬
    -0.07
    ä¸ĵ项治çIJĨ
    -0.07
    гина
    -0.07
    POSITIVE LOGITS
    å¹³åĿĩ
    0.08
    çļĦå¹³åĿĩ
    0.08
    å¹³åĿĩæ¯ı
    0.08
     average
    0.08
    average
    0.07
    å¹´å¹³åĿĩ
    0.07
    对è¿Ļ
    0.07
    æİ¥åıĹçļĦ
    0.06
    æĪijè¦ģè¯Ħ论
    0.06
    LOY
    0.06
    Activations Density 0.083%

    No Known Activations