© 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. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 61880
    Prev
    Next
    INDEX
    Explanations

    fructose or sugar sweeteners

    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
    Negative Logits
    EMENT
    -0.10
     ISSN
    -0.09
     oscillator
    -0.09
    alles
    -0.08
    nard
    -0.08
    AbsolutePath
    -0.08
    isto
    -0.08
     stat
    -0.08
     Ess
    -0.07
     Patch
    -0.07
    POSITIVE LOGITS
     Bender
    0.10
    ouns
    0.08
     Zus
    0.08
    sz
    0.08
    IRTUAL
    0.08
    (es
    0.08
     pz
    0.08
    wid
    0.08
    ional
    0.08
    pez
    0.08
    Activations Density 0.020%

    No Known Activations