© 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. 10538
    Prev
    Next
    INDEX
    Explanations

    words ending in -acy or -ometer

    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
    andy
    -0.07
    ä¸įå°ijçļĦ
    -0.06
    ogi
    -0.06
    èij
    -0.06
     rest
    -0.06
     Luk
    -0.06
    çī
    -0.05
    Rest
    -0.05
    çłĤæµĨ
    -0.05
     separ
    -0.05
    POSITIVE LOGITS
    icola
    0.07
    hers
    0.07
    缸çĪ±
    0.07
    ican
    0.07
    artic
    0.07
    æĵ
    0.07
    peg
    0.07
     Hers
    0.07
    =bool
    0.07
    новиÑĩ
    0.07
    Activations Density 0.062%

    No Known Activations