© 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. 8555
    Prev
    Next
    INDEX
    Explanations

    coated Fe3O4

    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
     Cosmetic
    -0.12
    .ui
    -0.10
     cosmetic
    -0.10
    ulet
    -0.10
    alia
    -0.10
     bella
    -0.10
    .gui
    -0.10
    .GUI
    -0.10
    ucci
    -0.09
    .UI
    -0.09
    POSITIVE LOGITS
     strugg
    0.07
     CPU
    0.07
    uran
    0.07
     DVR
    0.07
    .Unmarshal
    0.07
    é¾
    0.07
     subj
    0.07
    Backend
    0.06
     prolet
    0.06
    _integral
    0.06
    Activations Density 1.512%

    No Known Activations