© 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. 58899
    Prev
    Next
    INDEX
    Explanations

    splitting text content

    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
    au
    -0.09
     Presbyterian
    -0.08
    ous
    -0.08
    aux
    -0.08
     stab
    -0.07
     Pier
    -0.07
    al
    -0.07
    auf
    -0.07
    ant
    -0.07
    Builder
    -0.07
    POSITIVE LOGITS
    ting
    0.19
    tering
    0.15
    ter
    0.15
    ters
    0.13
    tered
    0.12
    tern
    0.12
    tere
    0.12
    tery
    0.12
    tons
    0.11
    tier
    0.11
    Activations Density 0.007%

    No Known Activations