© 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. 5019
    Prev
    Next
    INDEX
    Explanations

    Because" explains the following

    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
    öt
    -0.10
    utenant
    -0.10
    .cc
    -0.09
    æŃ¢
    -0.09
    apat
    -0.09
    .ac
    -0.09
    resas
    -0.09
    öm
    -0.09
     Energ
    -0.09
    PLICATION
    -0.09
    POSITIVE LOGITS
     Til
    0.09
     Robertson
    0.09
    ono
    0.09
    anz
    0.08
     value
    0.08
     sail
    0.07
     fres
    0.07
    ef
    0.07
     surf
    0.07
    arest
    0.07
    Activations Density 0.090%

    No Known Activations