© 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. 61684
    Prev
    Next
    INDEX
    Explanations

    Åij

    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
     bonded
    -0.06
     ret
    -0.06
     chalk
    -0.06
     dred
    -0.06
     segue
    -0.06
     unst
    -0.06
     под
    -0.06
    &q
    -0.06
     Der
    -0.06
     Proj
    -0.06
    POSITIVE LOGITS
    Åij
    0.11
    GT
    0.11
    idan
    0.10
    jid
    0.10
    orest
    0.10
    OW
    0.10
    ardon
    0.09
     Naked
    0.09
     Oc
    0.09
     Mathematical
    0.09
    Activations Density 0.002%

    No Known Activations