© 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. 4961
    Prev
    Next
    INDEX
    Explanations

    acknowledgement or agreement

    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
    UA
    -0.09
     Pool
    -0.09
     pool
    -0.08
    uffle
    -0.08
    edb
    -0.08
    usher
    -0.08
     sup
    -0.08
     fond
    -0.08
    issy
    -0.08
    imet
    -0.08
    POSITIVE LOGITS
    lahoma
    0.13
    AY
    0.11
    tober
    0.10
    hots
    0.10
    anagan
    0.10
    ra
    0.09
    oro
    0.09
    gor
    0.09
    ays
    0.09
    ño
    0.09
    Activations Density 0.084%

    No Known Activations