© 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. 3408
    Prev
    Next
    INDEX
    Explanations

    than we/they/ever/last/the

    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
    halb
    -0.11
     Lite
    -0.11
    gger
    -0.11
    arius
    -0.09
    idth
    -0.09
     ander
    -0.09
     Interstate
    -0.09
     lip
    -0.08
    atters
    -0.08
    casts
    -0.08
    POSITIVE LOGITS
    ynchronously
    0.08
    ков
    0.08
    enden
    0.08
    phy
    0.08
    oly
    0.07
    amo
    0.07
    xia
    0.07
    hos
    0.07
     ever
    0.07
    engl
    0.07
    Activations Density 0.080%

    No Known Activations