© 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. 690
    Prev
    Next
    INDEX
    Explanations

    It followed by 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
     Holt
    -0.10
     Le
    -0.08
     bod
    -0.08
     itu
    -0.08
    emy
    -0.08
     Hof
    -0.08
     nailed
    -0.08
    iet
    -0.08
     owe
    -0.08
    hex
    -0.08
    POSITIVE LOGITS
    unes
    0.27
    chy
    0.26
    iner
    0.25
    inerary
    0.25
    achi
    0.22
    alic
    0.21
    asca
    0.19
    aly
    0.18
    ching
    0.18
    ches
    0.17
    Activations Density 0.753%

    No Known Activations