© 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. 8185
    Prev
    Next
    INDEX
    Explanations

    light followed by adjectives or nouns

    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
     optical
    -0.11
     optics
    -0.11
    hof
    -0.10
    ilk
    -0.10
    hari
    -0.10
     Optical
    -0.10
    asc
    -0.10
     optic
    -0.09
     vision
    -0.09
    visibility
    -0.09
    POSITIVE LOGITS
    ened
    0.13
    est
    0.13
    ening
    0.12
    ed
    0.12
    -weight
    0.11
    -hearted
    0.11
    -duty
    0.11
     Fantastic
    0.10
    bourne
    0.10
    weight
    0.10
    Activations Density 0.114%

    No Known Activations