© 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. 46782
    Prev
    Next
    INDEX
    Explanations

    steel guitar

    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
    ul
    -0.06
    åħĪè¡Į
    -0.06
    abe
    -0.06
    ↵
    -0.06
     tens
    -0.06
    å¾Ĺ
    -0.05
    éĶħ
    -0.05
     (
    -0.05
    å·Ŀ
    -0.05
    abet
    -0.05
    POSITIVE LOGITS
    inois
    0.10
     bì
    0.09
    endis
    0.09
    جرÙĬ
    0.08
    ousel
    0.08
     cram
    0.08
     sema
    0.08
    .eof
    0.08
    ctest
    0.08
    endam
    0.08
    Activations Density 0.020%

    No Known Activations