© 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. 3650
    Prev
    Next
    INDEX
    Explanations

    energy conversion and forms

    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
     Salz
    -0.07
    åįĴ
    -0.07
    åİĨåı²æĸĩåĮĸ
    -0.07
    Normals
    -0.07
     pasaran
    -0.07
    çļĦ人äºĭ
    -0.07
    Å¡i
    -0.07
     гипеÑĢ
    -0.07
     seguid
    -0.07
    LOG
    -0.07
    POSITIVE LOGITS
    èĥ½éĩıçļĦ
    0.11
     energy
    0.11
    èĥ½éĩı
    0.10
    çļĦèĥ½éĩı
    0.10
    energy
    0.10
    -energy
    0.10
    转åĮĸ
    0.10
    转æį¢
    0.10
    å®ĪæģĴ
    0.09
    _energy
    0.09
    Activations Density 0.006%

    No Known Activations