© 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. 629
    Prev
    Next
    INDEX
    Explanations

    was/been followed by past participle

    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
     differing
    -0.10
     went
    -0.10
    iswa
    -0.10
    '↵↵↵↵
    -0.09
     originating
    -0.09
    trail
    -0.09
     headed
    -0.09
     ate
    -0.09
     clipped
    -0.09
     dissent
    -0.09
    POSITIVE LOGITS
     given
    0.12
     seen
    0.11
    thinkable
    0.09
     thought
    0.09
     ups
    0.09
    /is
    0.09
     used
    0.08
     subject
    0.08
     prefer
    0.08
     put
    0.08
    Activations Density 1.736%

    No Known Activations