© 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. 61441
    Prev
    Next
    INDEX
    Explanations

    legal case names or citations

    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
    illac
    -0.12
    igner
    -0.12
    asin
    -0.11
     >↵↵
    -0.11
    érica
    -0.11
    nameof
    -0.11
    abis
    -0.11
    oard
    -0.11
    .inst
    -0.10
    NECT
    -0.10
    POSITIVE LOGITS
    ç«
    0.08
     legion
    0.06
    avel
    0.06
     Hak
    0.06
    Tier
    0.06
    itz
    0.05
     OLD
    0.05
    etto
    0.05
     deer
    0.05
    .Maybe
    0.05
    Activations Density 0.032%

    No Known Activations