© 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. 54031
    Prev
    Next
    INDEX
    Explanations

    ontology, epistemology, metaphysics

    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
    ael
    -0.09
     Integrated
    -0.08
    ilar
    -0.08
    al
    -0.08
    OUSE
    -0.08
    iphone
    -0.07
     intact
    -0.07
    assic
    -0.07
    aco
    -0.07
    ouse
    -0.07
    POSITIVE LOGITS
    EMA
    0.11
     busiest
    0.10
    mits
    0.09
     Guinness
    0.09
    ivism
    0.09
     busy
    0.09
    $m
    0.09
     pledged
    0.09
     hang
    0.09
    UF
    0.09
    Activations Density 0.005%

    No Known Activations