© 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. 32427
    Prev
    Next
    INDEX
    Explanations

    galaxy formation and evolution

    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
    Setter
    -0.08
    owers
    -0.07
     memorandum
    -0.07
     formulation
    -0.07
    æľºä¸Ĭ
    -0.06
    æµģéĢļ
    -0.06
     sada
    -0.06
     Seger
    -0.06
     dispatch
    -0.06
    èĽŁé¾Ļ
    -0.06
    POSITIVE LOGITS
     galaxies
    0.10
    æĺŁç³»
    0.10
     outskirts
    0.09
     galaxy
    0.09
     supern
    0.09
    çŃī大åŀĭ
    0.09
     remnants
    0.08
    gal
    0.08
    -scale
    0.08
     merg
    0.08
    Activations Density 0.030%

    No Known Activations