© 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. 4785
    Prev
    Next
    INDEX
    Explanations

    punctuations and conjunctions in lists

    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
    orz
    -0.09
     veto
    -0.09
     neigh
    -0.09
    een
    -0.08
     zone
    -0.08
    ball
    -0.08
     loaf
    -0.08
    Nice
    -0.08
    itures
    -0.08
    ees
    -0.08
    POSITIVE LOGITS
    &P
    0.09
     Pays
    0.08
    gy
    0.08
     Cheat
    0.08
     Pou
    0.07
    )?.
    0.07
    finally
    0.07
    affer
    0.07
    ำ
    0.07
     Cock
    0.07
    Activations Density 0.700%

    No Known Activations