© 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. 61678
    Prev
    Next
    INDEX
    Explanations

    after and before context

    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
    asco
    -0.09
    Tube
    -0.09
    ifi
    -0.08
    462
    -0.07
    ions
    -0.07
    obb
    -0.07
    ож
    -0.07
    row
    -0.07
    week
    -0.07
    ola
    -0.07
    POSITIVE LOGITS
    lope
    0.11
    ees
    0.09
     flooded
    0.09
    haft
    0.09
    wit
    0.08
    oha
    0.08
    tat
    0.08
    ære
    0.08
    tn
    0.08
    alian
    0.08
    Activations Density 0.027%

    No Known Activations