© 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. 8694
    Prev
    Next
    INDEX
    Explanations

    what is called

    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
     Benn
    -0.09
    esch
    -0.09
    rij
    -0.08
     existed
    -0.08
    emos
    -0.08
    SENS
    -0.08
     banned
    -0.07
     sens
    -0.07
    XS
    -0.07
     outer
    -0.07
    POSITIVE LOGITS
    称
    0.12
     collo
    0.11
     termed
    0.11
     called
    0.09
    oge
    0.09
    Called
    0.09
    called
    0.08
    ffe
    0.08
     topping
    0.08
     Called
    0.08
    Activations Density 0.116%

    No Known Activations