© 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. 10279
    Prev
    Next
    INDEX
    Explanations

    code and commands

    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
    öny
    -0.07
    emento
    -0.07
    yn
    -0.06
    urang
    -0.06
    oretical
    -0.06
     ãĢĤ
    -0.06
    elten
    -0.06
     ↵    ↵
    -0.06
    _compat
    -0.06
    ilot
    -0.06
    POSITIVE LOGITS
    éªı
    0.09
    abas
    0.08
    شد
    0.08
     деÑģÑı
    0.08
     `$
    0.08
    sch
    0.08
    丽ä¸Ŀ
    0.08
    ache
    0.08
    acie
    0.08
    agne
    0.08
    Activations Density 0.035%

    No Known Activations