© 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. 8844
    Prev
    Next
    INDEX
    Explanations

    license agreements

    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
    ati
    -0.10
     handc
    -0.09
    anto
    -0.09
    าร
    -0.09
    주
    -0.09
    eras
    -0.09
     unc
    -0.09
     dismant
    -0.09
    +:
    -0.09
     burg
    -0.09
    POSITIVE LOGITS
    oe
    0.11
    ipes
    0.08
    isko
    0.08
    ools
    0.07
     ul
    0.07
     dumping
    0.07
    atak
    0.07
    ope
    0.07
     Rose
    0.07
    -fw
    0.07
    Activations Density 0.013%

    No Known Activations