© 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. 11826
    Prev
    Next
    INDEX
    Explanations

    indefinite article a or an

    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
    èĮĥæĸĩç½ij
    -0.08
    intree
    -0.08
    arote
    -0.07
    æĦ
    -0.07
    hut
    -0.07
    ató
    -0.07
    åħ®
    -0.07
    ÙĬÙģÙĬØ©
    -0.07
    ingas
    -0.07
    Monad
    -0.06
    POSITIVE LOGITS
    ืà¸Ńà¸ģ
    0.07
    çİ®
    0.07
    .fm
    0.06
     semula
    0.06
    ullet
    0.06
    ains
    0.06
    åĨħåľ°
    0.06
    alar
    0.06
    uro
    0.06
     Win
    0.06
    Activations Density 0.011%

    No Known Activations