© 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. 2998
    Prev
    Next
    INDEX
    Explanations

    historical research and discoveries

    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
     techn
    -0.10
    JUnit
    -0.09
    abort
    -0.08
     Gew
    -0.08
    ici
    -0.08
     globals
    -0.08
    lse
    -0.08
    æīĭ
    -0.08
     panicked
    -0.08
     Cyprus
    -0.08
    POSITIVE LOGITS
     historians
    0.15
     excav
    0.14
     excavation
    0.14
     historian
    0.13
     restoration
    0.13
     reconstruct
    0.12
     histor
    0.12
     reconstruction
    0.12
     unearth
    0.12
     Monument
    0.11
    Activations Density 0.450%

    No Known Activations