© 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. 1834
    Prev
    Next
    INDEX
    Explanations

    and other items

    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
     either
    -0.09
    uml
    -0.08
    enames
    -0.08
     besides
    -0.08
     sorte
    -0.08
    either
    -0.08
    _both
    -0.08
    [++
    -0.08
    emy
    -0.07
    %A
    -0.07
    POSITIVE LOGITS
     associated
    0.17
     its
    0.16
     accompanying
    0.16
     related
    0.16
     surrounding
    0.14
     Its
    0.13
     adjoining
    0.13
     attendant
    0.12
     other
    0.12
     their
    0.11
    Activations Density 1.839%

    No Known Activations