© 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. 51659
    Prev
    Next
    INDEX
    Explanations

    orbital motion and instability

    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
     Basis
    -0.06
    жо
    -0.06
    omagnet
    -0.06
    äºĴ为
    -0.06
    纯æŃ£
    -0.06
    èĥİ
    -0.06
    urit
    -0.06
    çŃı
    -0.06
    adian
    -0.06
     dese
    -0.06
    POSITIVE LOGITS
    çIJĨ论çłĶ究
    0.08
    ä»Ĭå¤ľ
    0.08
    èķĥ
    0.08
    lify
    0.08
    ä¸īåĮº
    0.08
     Shr
    0.08
    空头
    0.08
    -sw
    0.08
    scalar
    0.08
     shrinking
    0.08
    Activations Density 0.002%

    No Known Activations