© 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. 61658
    Prev
    Next
    INDEX
    Explanations

    numbers and letters following context indicators

    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
    иÑģÑĤ
    -0.10
    zee
    -0.10
    yar
    -0.09
    ;charset
    -0.09
    æ¥
    -0.09
     pk
    -0.08
    —one
    -0.08
     Instances
    -0.08
    ayan
    -0.08
     Sessions
    -0.08
    POSITIVE LOGITS
    apa
    0.09
     Venez
    0.08
     hopefully
    0.08
    ecret
    0.08
    unn
    0.08
    aos
    0.08
     yourselves
    0.08
    osed
    0.07
    xxxx
    0.07
    izzo
    0.07
    Activations Density 0.039%

    No Known Activations