© 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. 8224
    Prev
    Next
    INDEX
    Explanations

    objects, systems, world

    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
    andom
    -0.10
     */↵↵↵↵
    -0.10
    strap
    -0.10
     jac
    -0.10
    .Areas
    -0.09
    asso
    -0.09
     ж
    -0.09
     Reco
    -0.09
    иÑĢ
    -0.09
    .currentTarget
    -0.09
    POSITIVE LOGITS
     directly
    0.13
    .But
    0.10
     whereas
    0.10
    âĢ¦but
    0.10
     alone
    0.10
     rather
    0.10
     individual
    0.09
     physical
    0.09
     mechanically
    0.09
     Alone
    0.09
    Activations Density 0.668%

    No Known Activations