© 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. 31385
    Prev
    Next
    INDEX
    Explanations

    version numbers and package names

    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
    Ø©
    -0.12
    ing
    -0.10
    ات
    -0.10
    ت
    -0.09
    i
    -0.09
    ÙĬØ©
    -0.07
    ity
    -0.07
    éħ¸çĽIJ
    -0.07
    atson
    -0.07
    abl
    -0.07
    POSITIVE LOGITS
    .press
    0.08
    佬
    0.08
    ÑĮÑİ
    0.08
    ÙģÙĪر
    0.08
    å·¢
    0.07
    vertisement
    0.07
    ongyang
    0.07
    rial
    0.07
    ffer
    0.07
    culate
    0.07
    Activations Density 0.027%

    No Known Activations