© 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. 8825
    Prev
    Next
    INDEX
    Explanations

    names ending in 'ew'

    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
    way
    -0.09
     upt
    -0.09
    ways
    -0.09
    hv
    -0.08
    hausen
    -0.08
    cloth
    -0.08
    upt
    -0.08
    ough
    -0.08
    amac
    -0.07
    une
    -0.07
    POSITIVE LOGITS
    icz
    0.16
    á»įn
    0.12
    aters
    0.11
    ski
    0.11
    itz
    0.11
    orld
    0.11
    es
    0.11
    alker
    0.11
    een
    0.11
    ett
    0.11
    Activations Density 0.251%

    No Known Activations