© 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. 2306
    Prev
    Next
    INDEX
    Explanations

    could followed by a verb

    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
    PECIAL
    -0.09
    't
    -0.09
     gladly
    -0.09
    ÃŃt
    -0.09
     would
    -0.09
    access
    -0.08
    una
    -0.08
    GLISH
    -0.08
    ’t
    -0.08
    ds
    -0.08
    POSITIVE LOGITS
    ed
    0.09
    ness
    0.09
    ion
    0.09
    ered
    0.09
    ’ve
    0.09
    s
    0.09
    ily
    0.09
    erin
    0.09
    ering
    0.09
    well
    0.09
    Activations Density 0.075%

    No Known Activations