© 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. 48579
    Prev
    Next
    INDEX
    Explanations

    preserving state or conditions

    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
    usat
    -0.08
    %c
    -0.07
    mous
    -0.06
    adapter
    -0.06
    vg
    -0.06
     Adapter
    -0.06
    _OM
    -0.06
    apollo
    -0.06
    pecially
    -0.06
    (SK
    -0.06
    POSITIVE LOGITS
    å¿ħ须符åIJĪ
    0.08
    æĪijè¿ĺè¦ģ
    0.08
    éĤĦè¦ģ
    0.08
    ä¸įè¦ģ太
    0.07
    ToDevice
    0.07
    FolderPath
    0.07
    满足
    0.07
    osan
    0.07
     satisfy
    0.07
    actual
    0.07
    Activations Density 0.004%

    No Known Activations