© 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. 63432
    Prev
    Next
    INDEX
    Explanations

    snapshot; prevalence; year-end

    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
    达产年
    -0.08
    IPH
    -0.08
    à¸łà¸´
    -0.08
    PerPixel
    -0.07
    å¾ĹäºĨ
    -0.07
    جÙĬ
    -0.07
     avs
    -0.07
    zell
    -0.07
     Shak
    -0.07
    Sequential
    -0.07
    POSITIVE LOGITS
     snapshot
    0.13
     snapshots
    0.12
    å¿«çħ§
    0.12
    snapshot
    0.11
    å®ļæł¼
    0.10
     Snapshot
    0.10
    _snapshot
    0.10
    _snap
    0.09
    Snapshot
    0.09
    snap
    0.09
    Activations Density 0.041%

    No Known Activations