© 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. 39400
    Prev
    Next
    INDEX
    Explanations

    orbital eccentricity and celestial bodies

    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
    uret
    -0.07
     chor
    -0.07
    é½IJ
    -0.07
    åį¿
    -0.06
    assel
    -0.06
     omnip
    -0.06
     overload
    -0.06
    æĸŁéħĮ
    -0.06
     indis
    -0.06
     Domino
    -0.06
    POSITIVE LOGITS
     orbit
    0.08
    cky
    0.08
     Marte
    0.08
    plor
    0.08
    轨éģĵ
    0.07
    ợ
    0.07
     orbits
    0.07
     Bima
    0.07
    alendar
    0.07
    å¾Ģè¿Ķ
    0.07
    Activations Density 0.004%

    No Known Activations