© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2307
    Prev
    Next
    INDEX
    Explanations

    squared numbers

    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
    .navigateTo
    -0.07
    гелÑĮ
    -0.07
    ikal
    -0.07
     Killer
    -0.07
    eke
    -0.07
    æį¢æĪIJ
    -0.06
    滨海
    -0.06
    çĤ¹èĩ³
    -0.06
     Barber
    -0.06
     Ñħода
    -0.06
    POSITIVE LOGITS
    isson
    0.08
    Ĵáŀ
    0.07
    lhs
    0.07
    Ø·ÙĦ
    0.07
    ocache
    0.07
    ibase
    0.07
    æħ®
    0.06
    úst
    0.06
    éĨ
    0.06
    ints
    0.06
    Activations Density 0.004%

    No Known Activations