© 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. 34607
    Prev
    Next
    INDEX
    Explanations

    spacetime universe cosmology relational metrics

    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
    esson
    -0.08
    Ïģαί
    -0.08
    othing
    -0.08
     Blasio
    -0.08
    .removeAll
    -0.08
    FromClass
    -0.08
    ieger
    -0.08
    essen
    -0.08
    egin
    -0.08
    ivre
    -0.07
    POSITIVE LOGITS
    æĹ¶ç©º
    0.07
    æļ´
    0.06
     Bel
    0.06
    à¸ŀล
    0.06
     Hoh
    0.06
    è¾
    0.06
    ÛĮتÛĮ
    0.06
    å¾ĦåIJij
    0.06
    æĸĩåĮĸæ°ĽåĽ´
    0.06
     spherical
    0.06
    Activations Density 0.007%

    No Known Activations