© 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. 4999
    Prev
    Next
    INDEX
    Explanations

    he she they

    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
    ymoon
    -0.11
    brig
    -0.10
     neither
    -0.10
     tanto
    -0.10
    ebb
    -0.10
     helm
    -0.10
    eer
    -0.10
     guest
    -0.10
    ecd
    -0.10
    ĮĢ
    -0.09
    POSITIVE LOGITS
    oola
    0.08
    reet
    0.07
     she
    0.07
     SEG
    0.07
    /to
    0.07
    She
    0.07
     slugg
    0.07
     vested
    0.06
    æ£
    0.06
    He
    0.06
    Activations Density 0.246%

    No Known Activations