© 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. 38658
    Prev
    Next
    INDEX
    Explanations

    divisions and sections

    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
    alker
    -0.07
    æĬĬå®ĥ们
    -0.07
    lify
    -0.07
    ä»Ģä¹Īåij¢
    -0.06
    irme
    -0.06
    iteli
    -0.06
    ¹
    -0.06
    RelativeTo
    -0.06
    Hints
    -0.06
    ://%
    -0.06
    POSITIVE LOGITS
     therein
    0.08
    vog
    0.07
     dort
    0.07
     darin
    0.07
    orang
    0.07
     оÑĤÑĤ
    0.07
    .fs
    0.07
    ìĿµ
    0.06
     Mora
    0.06
    енÑĮ
    0.06
    Activations Density 0.929%

    No Known Activations