© 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. 62204
    Prev
    Next
    INDEX
    Explanations

    technological or sales terms

    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
     laut
    -0.07
     Dok
    -0.07
    .optim
    -0.06
    ruk
    -0.06
    ISION
    -0.06
    æĽ´çĶŁ
    -0.06
     Jabar
    -0.06
    ÚĨÙĩ
    -0.06
    èĩªå¾ĭ
    -0.06
    çĻ½å±±
    -0.06
    POSITIVE LOGITS
    æľĢç»Īè¿ĺæĺ¯
    0.09
     comunque
    0.08
     again
    0.08
    again
    0.08
    ovol
    0.08
    è¿ĺæĺ¯ä¼ļ
    0.08
    çļĦè¿ĺæĺ¯
    0.08
    é¹ħ
    0.08
    ceed
    0.08
     nami
    0.08
    Activations Density 0.123%

    No Known Activations