© 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. 1051
    Prev
    Next
    INDEX
    Explanations

    it's done

    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
    ×ķ׼
    -0.07
    çļĦèµ°åĬ¿
    -0.07
    ewan
    -0.07
    ä½ķæ³ģ
    -0.06
    ago
    -0.06
    ä»ħ次äºİ
    -0.06
    走强
    -0.06
    è¿Ļæł·çļĦæĥħåĨµ
    -0.06
    å®ŀå±ŀ
    -0.06
    Einst
    -0.06
    POSITIVE LOGITS
    çģ
    0.08
    ingly
    0.08
    ãĥĥ
    0.07
    viel
    0.07
    ä¸įä½ıäºĨ
    0.07
     ÐŀпÑĥбликовано
    0.07
    çł¥
    0.07
    åķ¦
    0.07
    utherland
    0.07
    äºĨåįĬ天
    0.07
    Activations Density 0.028%

    No Known Activations