© 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. 54984
    Prev
    Next
    INDEX
    Explanations

    injection, catheter, pressure, withdrawn, controls, sites

    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
    ero
    -0.12
     surg
    -0.12
    ERO
    -0.11
    amus
    -0.10
     nostra
    -0.10
     yer
    -0.10
    anon
    -0.10
    pra
    -0.10
     deprived
    -0.10
     helicopt
    -0.10
    POSITIVE LOGITS
     Nest
    0.07
     plaisir
    0.07
     confirming
    0.06
     dwell
    0.06
    -confirm
    0.06
     Zo
    0.06
    ité
    0.06
    æ³
    0.06
     upstream
    0.06
     Hill
    0.06
    Activations Density 0.007%

    No Known Activations