© 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. 22507
    Prev
    Next
    INDEX
    Explanations

    benchmark calculations

    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
    å¨ħ
    -0.08
    éĤ¦
    -0.07
    à´£àµį
    -0.07
    asd
    -0.07
    owa
    -0.07
    çIJ¥
    -0.07
    Äįer
    -0.07
     crumbs
    -0.07
    uuid
    -0.07
    èı²åĪ©
    -0.07
    POSITIVE LOGITS
    atables
    0.08
    benchmark
    0.08
    èĩªæĿ¥
    0.07
     benchmark
    0.07
    Benchmark
    0.07
     Benchmark
    0.07
    lid
    0.07
    å¿ĥçĹĽ
    0.06
    illion
    0.06
    çī¹æĢ§
    0.06
    Activations Density 0.022%

    No Known Activations