© 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. 550
    Prev
    Next
    INDEX
    Explanations

    two, both, pair, respectively

    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
     Various
    -0.12
     various
    -0.11
    Various
    -0.11
     itself
    -0.11
    —all
    -0.11
     all
    -0.10
     ALL
    -0.10
    =all
    -0.10
    (all
    -0.10
    ?,?,
    -0.10
    POSITIVE LOGITS
     respectively
    0.32
     respective
    0.28
     two
    0.22
    两
    0.22
     halves
    0.20
    respect
    0.19
     both
    0.19
     Both
    0.19
    two
    0.18
     separately
    0.18
    Activations Density 2.585%

    No Known Activations