© 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. 489
    Prev
    Next
    INDEX
    Explanations

    nature of importance

    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
     bureaucr
    -0.09
     fier
    -0.08
     fict
    -0.08
     unthinkable
    -0.08
    rote
    -0.07
    irable
    -0.07
     foremost
    -0.07
     ug
    -0.07
     essentials
    -0.07
    ht
    -0.07
    POSITIVE LOGITS
     fact
    0.21
     nature
    0.21
     lack
    0.20
     inability
    0.17
     similarities
    0.16
     ease
    0.15
     inherent
    0.15
     ability
    0.14
     similarity
    0.13
     availability
    0.13
    Activations Density 1.479%

    No Known Activations