© 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. 49549
    Prev
    Next
    INDEX
    Explanations

    disconnected components or disjoint sets

    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
    åIJIJ
    -0.08
    tec
    -0.08
    CRET
    -0.07
    WW
    -0.07
    lew
    -0.07
    家家
    -0.07
    缴åij¼
    -0.07
    ä¸Ģ代
    -0.07
    vert
    -0.06
    stone
    -0.06
    POSITIVE LOGITS
    -separated
    0.09
     separated
    0.09
    eld
    0.08
    島
    0.08
    ãģ«åĪĨ
    0.08
     separate
    0.08
    大å°ı为
    0.08
     disconnected
    0.08
    åĪĨéļĶ
    0.08
    åĪĨ离
    0.08
    Activations Density 0.005%

    No Known Activations