© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 590
    Prev
    Next
    INDEX
    Explanations

    in phrases like "in fact", "in case"

    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
    gether
    -0.14
    oretical
    -0.10
     in
    -0.10
    neath
    -0.10
    theless
    -0.10
    oret
    -0.09
    day
    -0.09
    ories
    -0.08
    ynchronously
    -0.08
    how
    -0.08
    POSITIVE LOGITS
     accordance
    0.20
    sofar
    0.19
    quis
    0.19
    /out
    0.18
    compat
    0.18
     conjunction
    0.18
     order
    0.18
    -house
    0.17
    appropri
    0.17
     terms
    0.17
    Activations Density 2.105%

    No Known Activations