© 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. 57519
    Prev
    Next
    INDEX
    Explanations

    and next

    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
     Haz
    -0.10
     Pin
    -0.09
     pin
    -0.09
     exc
    -0.08
    hu
    -0.08
    ecs
    -0.08
     Exc
    -0.08
     strategically
    -0.08
     either
    -0.08
     dunk
    -0.08
    POSITIVE LOGITS
    faf
    0.08
     Shack
    0.08
    dry
    0.08
    .Chrome
    0.08
     plateau
    0.08
    uppe
    0.08
    able
    0.08
     Middleton
    0.08
    ered
    0.07
     Barber
    0.07
    Activations Density 0.002%

    No Known Activations