© 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. 8880
    Prev
    Next
    INDEX
    Explanations

    dynamic behavior

    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
    iot
    -0.10
    ril
    -0.09
    wal
    -0.09
     Sid
    -0.09
    beck
    -0.09
    wap
    -0.09
     champagne
    -0.09
    ков
    -0.08
    åı·
    -0.08
    RAL
    -0.08
    POSITIVE LOGITS
     duo
    0.10
    erin
    0.08
    stor
    0.08
    vers
    0.08
    asty
    0.08
    esty
    0.08
    ahoo
    0.07
     Cro
    0.07
    .ol
    0.07
     Fee
    0.07
    Activations Density 0.154%

    No Known Activations