© 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. 57589
    Prev
    Next
    INDEX
    Explanations

    programming related terms

    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
    ucha
    -0.08
    åIJĦéĥ¨
    -0.08
    åĵªä¸Ģç§į
    -0.08
    ahu
    -0.07
    rowsers
    -0.07
     mainten
    -0.07
    unjung
    -0.07
    ÙĨز
    -0.07
     /^\
    -0.07
    £¼
    -0.07
    POSITIVE LOGITS
    ä»»æĦı
    0.07
     multiples
    0.07
     arbitrarily
    0.07
    羡
    0.07
     writable
    0.06
    äºĴ缸
    0.06
    .setdefault
    0.06
    .WriteByte
    0.06
    çĵ¦
    0.06
    é¾ĻéŨ
    0.06
    Activations Density 0.010%

    No Known Activations