© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 58336
    Prev
    Next
    INDEX
    Explanations

    references, citations

    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
     historically
    -0.11
     empir
    -0.10
     +/-
    -0.09
    avl
    -0.09
     observations
    -0.09
     arguably
    -0.09
    lbl
    -0.09
     USDA
    -0.09
     anecd
    -0.09
     tud
    -0.08
    POSITIVE LOGITS
    .CO
    0.09
     futuristic
    0.08
     Pand
    0.08
     congrat
    0.08
    npj
    0.08
     haus
    0.08
    seed
    0.08
     Porter
    0.08
    sing
    0.07
    ivre
    0.07
    Activations Density 0.027%

    No Known Activations