© 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. 18904
    Prev
    Next
    INDEX
    Explanations

    neutron star and white dwarf properties

    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
     Seger
    -0.08
    angsa
    -0.07
    microsoft
    -0.07
    fork
    -0.07
    梳
    -0.07
    大æĬĬ
    -0.07
     wild
    -0.07
    wild
    -0.07
    atchet
    -0.07
    æ³³
    -0.07
    POSITIVE LOGITS
     compact
    0.08
    enos
    0.07
     UNU
    0.07
    éĻĢ
    0.07
     slab
    0.07
     slam
    0.07
    compact
    0.07
    åİĭç´§
    0.07
    åİĭ强
    0.07
    (compact
    0.07
    Activations Density 0.008%

    No Known Activations