© 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. 61150
    Prev
    Next
    INDEX
    Explanations

    wherever, when, exact locations

    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
    stakes
    -0.12
    iest
    -0.10
    fad
    -0.09
    uch
    -0.09
    cef
    -0.09
    еж
    -0.09
    uga
    -0.09
    onto
    -0.09
    pit
    -0.09
    Mapped
    -0.09
    POSITIVE LOGITS
    plat
    0.09
    0.08
     gym
    0.08
     whenever
    0.08
    amon
    0.08
    s
    0.07
    dn
    0.07
    igu
    0.07
     continuity
    0.07
     propos
    0.07
    Activations Density 0.011%

    No Known Activations