© 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. 4710
    Prev
    Next
    INDEX
    Explanations

    qualification phrases

    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
    UNS
    -0.10
     Democr
    -0.10
     ugl
    -0.10
     inexp
    -0.10
    opi
    -0.10
    ois
    -0.10
    loh
    -0.10
    andle
    -0.10
     ostensibly
    -0.09
    ibble
    -0.09
    POSITIVE LOGITS
     ox
    0.09
     gimm
    0.09
     merely
    0.08
    LB
    0.08
     intend
    0.08
     kits
    0.08
     cann
    0.08
     preach
    0.08
     bore
    0.08
    urgy
    0.08
    Activations Density 0.219%

    No Known Activations