© 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. 9592
    Prev
    Next
    INDEX
    Explanations

    eccentric or elliptical orbits

    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
    obao
    -0.07
     '`
    -0.06
    ään
    -0.06
    omnia
    -0.06
    .uk
    -0.06
    mon
    -0.06
     Brescia
    -0.06
    bou
    -0.06
    blick
    -0.06
    rano
    -0.06
    POSITIVE LOGITS
    çİĩ
    0.09
    çİĩçļĦ
    0.08
    æīĵæ³ķ
    0.08
    .archive
    0.08
    仪
    0.08
     whipping
    0.08
    IGO
    0.07
    ilis
    0.07
    iless
    0.07
    ischung
    0.07
    Activations Density 0.001%

    No Known Activations