© 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. 701
    Prev
    Next
    INDEX
    Explanations

    first followed by 'of', 'details', 'major', 'problem', 'month', 'beta', 'retrospective'

    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
    iÃŁ
    -0.07
    abo
    -0.07
    Ķ
    -0.07
    gnore
    -0.06
    ongo
    -0.06
     first
    -0.06
    gom
    -0.06
     presently
    -0.06
    ued
    -0.06
    é¦ĸ
    -0.06
    POSITIVE LOGITS
    -ever
    0.25
    born
    0.23
     impressions
    0.19
    -hand
    0.18
     responders
    0.18
    -person
    0.17
     glance
    0.17
    -rate
    0.17
    -order
    0.17
     impression
    0.16
    Activations Density 0.641%

    No Known Activations