© 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. 9866
    Prev
    Next
    INDEX
    Explanations

    Robertson-Walker spacetime; curvature

    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
     unpack
    -0.07
    æ²īé»ĺ
    -0.07
    DSP
    -0.07
    ä¸įä½ľä¸º
    -0.06
     Speak
    -0.06
    IZER
    -0.06
    æ¾ľ
    -0.06
    éľĨ
    -0.06
    Speak
    -0.06
    åħ¬å®³
    -0.06
    POSITIVE LOGITS
    åºķåŃIJ
    0.09
    immel
    0.08
    æĿŀ
    0.08
    datal
    0.08
    пелÑĮ
    0.08
     curvature
    0.08
     Sachs
    0.07
    à¸Ĺรà¸ĩ
    0.07
     cosm
    0.07
    patial
    0.07
    Activations Density 0.005%

    No Known Activations