© 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. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 54178
    Prev
    Next
    INDEX
    Explanations

    NOT TO BE PUBLISHED

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    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
     DISCLAIMER
    -0.09
     sparing
    -0.09
     lite
    -0.08
     surround
    -0.08
     downs
    -0.08
     caveat
    -0.08
     Insider
    -0.08
    ноп
    -0.08
     cogn
    -0.08
     caution
    -0.08
    POSITIVE LOGITS
     buc
    0.10
    aso
    0.09
     Dra
    0.09
    iate
    0.08
    frm
    0.08
    KN
    0.08
    overall
    0.08
    cca
    0.08
    Slave
    0.08
    Intro
    0.08
    Activations Density 0.005%

    No Known Activations