© 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. 91
    Prev
    Next
    INDEX
    Explanations

    models, simulating, recreate

    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
    emann
    -0.10
    oren
    -0.09
    ünd
    -0.09
     PIX
    -0.09
    egin
    -0.09
     Ùģ
    -0.09
    entries
    -0.08
    inspect
    -0.08
    estre
    -0.08
    -processing
    -0.08
    POSITIVE LOGITS
     simulate
    0.25
     sim
    0.22
     recre
    0.21
     recreate
    0.21
     simulated
    0.20
     simulation
    0.20
     mim
    0.19
     realistic
    0.19
    /mock
    0.18
     model
    0.18
    Activations Density 2.542%

    No Known Activations