© 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. 8295
    Prev
    Next
    INDEX
    Explanations

    never seen before

    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
    agh
    -0.11
     punch
    -0.10
     Brill
    -0.10
    Nation
    -0.10
    hetto
    -0.10
    awe
    -0.10
    BUM
    -0.10
    duct
    -0.09
    füh
    -0.09
    bones
    -0.09
    POSITIVE LOGITS
     ordinarily
    0.12
     previously
    0.12
     normally
    0.11
     Previously
    0.10
     accent
    0.09
    consider
    0.08
     usually
    0.08
     til
    0.08
     nor
    0.07
     concepts
    0.07
    Activations Density 0.196%

    No Known Activations