© 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. 53955
    Prev
    Next
    INDEX
    Explanations

    cross-appellant or counterattack

    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
    mage
    -0.10
    zÄĻ
    -0.10
    _then
    -0.10
     Clearance
    -0.10
    gue
    -0.09
     Hunting
    -0.09
     valign
    -0.09
    oice
    -0.09
    tty
    -0.09
    TableRow
    -0.09
    POSITIVE LOGITS
    anchor
    0.08
     Provid
    0.07
    wu
    0.07
     NYT
    0.07
     assim
    0.06
    iri
    0.06
    [:]
    0.06
    ned
    0.06
    erator
    0.06
     inherently
    0.06
    Activations Density 0.001%

    No Known Activations