© 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. 42654
    Prev
    Next
    INDEX
    Explanations

    required payments and expenses

    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
    ardino
    -0.08
    arde
    -0.07
    íĶĦëĿ¼
    -0.07
    è¯Ĺæĥħ
    -0.07
    ilde
    -0.07
    _inline
    -0.07
    plements
    -0.07
    СТÐŀ
    -0.07
    ampe
    -0.07
    udget
    -0.06
    POSITIVE LOGITS
    æīĢéľĢçļĦ
    0.12
    æīĢéľĢ
    0.10
     required
    0.10
     necessary
    0.09
    å¿ħè¦ģçļĦ
    0.09
    ecessary
    0.09
    required
    0.09
     plus
    0.09
     Required
    0.09
     needed
    0.08
    Activations Density 0.037%

    No Known Activations