© 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. 50
    Prev
    Next
    INDEX
    Explanations

    new or changed features

    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
     accumulate
    -0.09
     accumulating
    -0.09
     peculiar
    -0.09
    onda
    -0.09
    rente
    -0.08
     continually
    -0.08
     Accum
    -0.08
    yn
    -0.08
    alu
    -0.08
     loosely
    -0.08
    POSITIVE LOGITS
     new
    0.25
     newfound
    0.21
    /new
    0.20
    æĸ°
    0.18
    -new
    0.18
     changed
    0.18
     improved
    0.18
    new
    0.18
    (new
    0.17
     overhaul
    0.17
    Activations Density 3.277%

    No Known Activations