© 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. 54313
    Prev
    Next
    INDEX
    Explanations

    rates and levels

    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
    uft
    -0.09
    afb
    -0.09
    afs
    -0.09
    ches
    -0.09
     estimates
    -0.09
    Est
    -0.08
     estim
    -0.08
     Tamb
    -0.08
     billions
    -0.08
     switched
    -0.08
    POSITIVE LOGITS
     improvement
    0.15
     achievement
    0.13
     achievements
    0.12
     Improvement
    0.12
     improvements
    0.12
     progress
    0.11
    Achie
    0.10
     Achie
    0.10
     Progress
    0.10
     Achievement
    0.10
    Activations Density 0.071%

    No Known Activations