© 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. 17634
    Prev
    Next
    INDEX
    Explanations

    . 2

    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
    çĦ¶åIJİæł¹æį®
    -0.07
    anz
    -0.07
    å±Ģ
    -0.07
     Postar
    -0.07
    æľ¬åħ¬ä¼Ĺåı·
    -0.07
     **:**
    -0.07
    éĻ·
    -0.07
    maf
    -0.07
    emt
    -0.07
    andelt
    -0.07
    POSITIVE LOGITS
    å°ıçŁ¥è¯Ĩ
    0.08
    å°ı贴士
    0.07
    ↵↵
    0.06
     di
    0.06
    odiac
    0.06
    ixon
    0.06
    jata
    0.06
    转贴
    0.06
     bÃło
    0.06
    缸åħ³æĸĩç«ł
    0.06
    Activations Density 0.015%

    No Known Activations