© 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. 3905
    Prev
    Next
    INDEX
    Explanations

    lock

    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
    amar
    -0.09
    manship
    -0.09
    ed
    -0.09
    amon
    -0.09
    osity
    -0.08
     grounds
    -0.08
    shore
    -0.08
    imon
    -0.08
     inspection
    -0.08
    dom
    -0.08
    POSITIVE LOGITS
    jaw
    0.12
    ean
    0.11
     LOCK
    0.11
     horns
    0.10
     Lock
    0.10
    ï½¥
    0.10
    lea
    0.09
    quals
    0.09
    .lock
    0.09
    .Lock
    0.09
    Activations Density 0.121%

    No Known Activations