© 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. 4682
    Prev
    Next
    INDEX
    Explanations

    flat-bed, flat-screen, flat-backed, flat panel, flat spots

    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
    isin
    -0.10
    ',{
    -0.09
    lef
    -0.09
    OMP
    -0.09
    ìĹ´
    -0.09
    achu
    -0.09
    haar
    -0.09
     Estados
    -0.08
     fenced
    -0.08
     Nik
    -0.08
    POSITIVE LOGITS
    ulence
    0.15
    ening
    0.12
    ulent
    0.12
    bed
    0.11
    ened
    0.10
    ronic
    0.10
    lands
    0.10
    ting
    0.10
    bang
    0.10
    ness
    0.09
    Activations Density 0.055%

    No Known Activations