© 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. 3872
    Prev
    Next
    INDEX
    Explanations

    two or more entities

    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
     Uncomment
    -0.08
     zwischen
    -0.08
     alongside
    -0.08
    upe
    -0.07
    chin
    -0.07
     kol
    -0.07
    aty
    -0.07
     Multiple
    -0.07
     respective
    -0.07
     additional
    -0.07
    POSITIVE LOGITS
    ETH
    0.11
     forming
    0.10
     Together
    0.10
     together
    0.10
     pairwise
    0.10
    /modules
    0.10
    ANY
    0.10
     FAC
    0.09
     Spiel
    0.09
     arranged
    0.09
    Activations Density 0.358%

    No Known Activations