© 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. 61655
    Prev
    Next
    INDEX
    Explanations

    Mas followed by names or places

    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
    es
    -0.09
    y
    -0.09
    s
    -0.09
    sb
    -0.07
    i
    -0.07
    /connect
    -0.06
    esium
    -0.06
     Rally
    -0.06
    roy
    -0.06
    sa
    -0.06
    POSITIVE LOGITS
    ead
    0.12
    anko
    0.12
    aus
    0.12
    acent
    0.11
    cher
    0.11
    ering
    0.11
    ز
    0.11
    ques
    0.11
    usu
    0.11
    atab
    0.11
    Activations Density 0.023%

    No Known Activations