© 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. 3469
    Prev
    Next
    INDEX
    Explanations

    all about

    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
     all
    -0.13
    /all
    -0.12
     imaginable
    -0.12
    owing
    -0.11
     major
    -0.11
    place
    -0.11
     everything
    -0.10
    ones
    -0.10
     things
    -0.10
    THING
    -0.10
    POSITIVE LOGITS
    yc
    0.09
    scape
    0.08
     Bair
    0.07
    env
    0.07
     misunderstood
    0.07
     adoption
    0.07
     alone
    0.07
    apan
    0.07
    agua
    0.07
     abroad
    0.07
    Activations Density 0.076%

    No Known Activations