© 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. 54045
    Prev
    Next
    INDEX
    Explanations

    names of people, places, or organizations

    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
    Not in Any Lists

    No Comments

    Negative Logits
     CIM
    -0.08
    lock
    -0.08
    loe
    -0.08
    izar
    -0.07
     Rh
    -0.07
    lore
    -0.07
    halt
    -0.07
    poi
    -0.07
    hu
    -0.07
     rh
    -0.07
    POSITIVE LOGITS
    abis
    0.11
    aket
    0.09
     quot
    0.09
    NST
    0.09
     scop
    0.09
    _IL
    0.09
     tard
    0.09
    ented
    0.09
    INDOW
    0.09
    olec
    0.08
    Activations Density 0.063%

    No Known Activations