© 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. 8642
    Prev
    Next
    INDEX
    Explanations

    decided to do

    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
    /default
    -0.09
    ihar
    -0.09
     successfully
    -0.09
     Turnbull
    -0.08
     Municip
    -0.08
     sala
    -0.08
    -rights
    -0.08
     лÑİ
    -0.08
    enville
    -0.08
     desire
    -0.08
    POSITIVE LOGITS
    ALE
    0.09
     pursuing
    0.09
     tackling
    0.09
     rather
    0.09
    ipes
    0.09
    teil
    0.09
    ale
    0.09
     pursue
    0.09
    ari
    0.08
     spice
    0.08
    Activations Density 0.179%

    No Known Activations