© 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. 50244
    Prev
    Next
    INDEX
    Explanations

    universal, smallest, category

    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
    jol
    -0.07
    çĸĹåħ»
    -0.07
    ä¸įé½IJ
    -0.07
    wright
    -0.07
     Nab
    -0.07
    ollection
    -0.07
    бÑĢÑı
    -0.06
    ATR
    -0.06
     sal
    -0.06
    çļĦæľīæķĪ
    -0.06
    POSITIVE LOGITS
     uniqu
    0.08
     unique
    0.07
     principle
    0.07
    AAF
    0.07
     moc
    0.07
    ucha
    0.07
    tvr
    0.07
    .unique
    0.07
     Functor
    0.07
    çĭ¬çī¹
    0.07
    Activations Density 0.009%

    No Known Activations