© 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. 54631
    Prev
    Next
    INDEX
    Explanations

    mathematical operations

    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
    pf
    -0.10
    ty
    -0.10
     Ere
    -0.09
    ilent
    -0.09
    gressor
    -0.09
    ippet
    -0.09
    exion
    -0.09
    aken
    -0.09
     assembled
    -0.09
     unleashed
    -0.09
    POSITIVE LOGITS
    /Public
    0.08
    igu
    0.08
    gether
    0.08
    /App
    0.08
     medically
    0.07
    cer
    0.07
     Templates
    0.07
     Wor
    0.07
     nad
    0.07
    mer
    0.07
    Activations Density 0.002%

    No Known Activations