© 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. 63819
    Prev
    Next
    INDEX
    Explanations

    tunneling and related concepts

    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
    arters
    -0.08
    hart
    -0.07
     mond
    -0.07
     ord
    -0.07
    æĺ¯éĽĨ
    -0.06
    åıĺæĽ´åIJİ
    -0.06
    _increment
    -0.06
    eted
    -0.06
    gregator
    -0.06
    Swagger
    -0.06
    POSITIVE LOGITS
     tunn
    0.10
    æ¦Ĥçİĩ
    0.09
    渡åģĩ
    0.08
    åĩłçİĩ
    0.08
    çªģçł´
    0.08
     probability
    0.08
     tunnel
    0.08
    éĢļéģĵ
    0.08
    éļ§éģĵ
    0.08
    ç©¿éĢı
    0.08
    Activations Density 0.018%

    No Known Activations