© 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. 54030
    Prev
    Next
    INDEX
    Explanations

    conducted

    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
     prere
    -0.10
     spoilers
    -0.10
     crossword
    -0.10
    asn
    -0.09
    upos
    -0.09
    SPATH
    -0.09
    onus
    -0.09
    Sets
    -0.09
    nex
    -0.09
    -ce
    -0.08
    POSITIVE LOGITS
     retro
    0.10
     backwards
    0.10
     Retro
    0.09
    اØ
    0.09
     retrospective
    0.09
     backward
    0.09
     singled
    0.08
    adle
    0.08
     records
    0.08
    ingle
    0.07
    Activations Density 0.105%

    No Known Activations