© 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. 43237
    Prev
    Next
    INDEX
    Explanations

    total amount

    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
    -webpack
    -0.08
    ¾
    -0.08
     teb
    -0.07
    çĬĢ
    -0.07
    ismi
    -0.07
    示èĮĥæĢ§
    -0.07
    ieh
    -0.07
    羣çļĦè¦ģ
    -0.07
    دÙĪز
    -0.07
     ЧелÑı
    -0.07
    POSITIVE LOGITS
     total
    0.12
    æĢ»çļĦ
    0.12
    total
    0.11
     totalCount
    0.11
    æĢ»æķ°
    0.10
     totale
    0.10
    æĢ»
    0.10
    (total
    0.09
    _total
    0.09
    ,total
    0.09
    Activations Density 0.103%

    No Known Activations