© 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. 61690
    Prev
    Next
    INDEX
    Explanations

    concluding or elaborating on a preceding statement

    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
    so
    -0.11
    -Allow
    -0.09
    staking
    -0.09
    net
    -0.09
     so
    -0.09
    adj
    -0.09
     Seat
    -0.09
    lew
    -0.08
    cep
    -0.08
    FR
    -0.08
    POSITIVE LOGITS
    atis
    0.09
    rous
    0.09
    0.09
    uros
    0.08
     suck
    0.08
    ho
    0.08
    Uploaded
    0.08
    iseum
    0.07
    erde
    0.07
     Pg
    0.07
    Activations Density 0.022%

    No Known Activations