© 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. 3922
    Prev
    Next
    INDEX
    Explanations

    entities followed by descriptive clauses

    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
     widely
    -0.12
    fully
    -0.09
     kata
    -0.09
     known
    -0.09
     largely
    -0.09
     collabor
    -0.09
     admired
    -0.09
     Garten
    -0.09
    amel
    -0.09
     popular
    -0.09
    POSITIVE LOGITS
    olini
    0.09
    eu
    0.08
    ê¹
    0.08
    uments
    0.08
    lifetime
    0.08
     shy
    0.08
    uite
    0.07
     blink
    0.07
    Lifetime
    0.07
     Lifetime
    0.07
    Activations Density 0.207%

    No Known Activations