© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 8503
    Prev
    Next
    INDEX
    Explanations

    could use verbs

    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
     sometimes
    -0.12
     apparently
    -0.11
    ometimes
    -0.10
     usually
    -0.10
     thankfully
    -0.09
     generally
    -0.09
    sometimes
    -0.09
     typically
    -0.09
     mainly
    -0.09
     unfortunately
    -0.09
    POSITIVE LOGITS
     maybe
    0.17
     perhaps
    0.16
     could
    0.15
     Maybe
    0.14
     Perhaps
    0.13
    perhaps
    0.13
    maybe
    0.13
    could
    0.13
    Perhaps
    0.12
     Could
    0.12
    Activations Density 0.341%

    No Known Activations