© 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. 58794
    Prev
    Next
    INDEX
    Explanations

    UK news, leisure, communication, charge, protect

    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
     Boyle
    -0.08
     DOI
    -0.08
    DOI
    -0.08
    ĥĿ
    -0.07
    cean
    -0.07
    obe
    -0.07
     Boise
    -0.07
     Garner
    -0.07
    oden
    -0.06
    oods
    -0.06
    POSITIVE LOGITS
    ixa
    0.10
     Clo
    0.10
    china
    0.10
    -gallery
    0.10
    ÑģÑĭ
    0.10
    "struct
    0.10
     Clover
    0.09
    zos
    0.09
     offs
    0.09
    inet
    0.09
    Activations Density 0.234%

    No Known Activations