© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 37738
    Prev
    Next
    INDEX
    Explanations

    orthonormal frames or composition

    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
    -0.08
    ç¹ģåįİ
    -0.06
    ray
    -0.06
     opt
    -0.06
     wl
    -0.06
    æ··èĽĭ
    -0.06
     ties
    -0.06
     Tie
    -0.06
     Lil
    -0.06
     values
    -0.06
    POSITIVE LOGITS
     commuting
    0.08
     nowhere
    0.08
    èche
    0.08
    Äįin
    0.08
    ahoma
    0.07
    æ´»
    0.07
    itur
    0.07
    itaire
    0.07
    æĹłèĥ½
    0.07
    CHAIN
    0.07
    Activations Density 0.005%

    No Known Activations