© 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. 54942
    Prev
    Next
    INDEX
    Explanations

    objective-c collection types

    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
     scal
    -0.10
    enco
    -0.09
    sess
    -0.08
    -scal
    -0.08
    aten
    -0.08
    UG
    -0.08
    aign
    -0.08
    spr
    -0.08
     Stephan
    -0.08
     Cone
    -0.08
    POSITIVE LOGITS
    utor
    0.09
    ision
    0.09
     backing
    0.09
    connector
    0.09
    imal
    0.08
     cour
    0.08
    arter
    0.08
    ãĤº
    0.08
    kor
    0.08
    erk
    0.08
    Activations Density 0.001%

    No Known Activations