© 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. 2540
    Prev
    Next
    INDEX
    Explanations

    left and right branches

    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
    endung
    -0.07
    éné
    -0.07
    å¿ĹæĪIJ
    -0.07
    apur
    -0.06
    edy
    -0.06
    å¤ļ款
    -0.06
    é»İæĺİ
    -0.06
     europ
    -0.06
    Epoch
    -0.06
    Deb
    -0.06
    POSITIVE LOGITS
    /right
    0.10
    /left
    0.10
     subtree
    0.09
    asis
    0.08
    æł½
    0.08
     rutina
    0.08
    obr
    0.07
    SearchTree
    0.07
    routine
    0.07
    詳æĥħ
    0.07
    Activations Density 0.003%

    No Known Activations