© 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. 290
    Prev
    Next
    INDEX
    Explanations

    quantifying quantities or types

    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
     widest
    -0.10
     entire
    -0.10
     stupidity
    -0.09
     autobiography
    -0.09
     enf
    -0.09
     carr
    -0.08
     legislation
    -0.08
     biggest
    -0.08
    egin
    -0.08
     most
    -0.08
    POSITIVE LOGITS
     different
    0.19
     dozen
    0.16
     hundred
    0.15
     sclerosis
    0.15
     times
    0.15
    fold
    0.15
     (>
    0.15
     other
    0.15
    -many
    0.15
     thousand
    0.14
    Activations Density 1.090%

    No Known Activations