© 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. 57172
    Prev
    Next
    INDEX
    Explanations

    citations like [@B] or [@bib]

    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
    osis
    -0.08
     Reflect
    -0.07
     acc
    -0.07
    amped
    -0.07
     Dank
    -0.07
     Townsend
    -0.07
     Wich
    -0.06
     putt
    -0.06
     undisclosed
    -0.06
    628
    -0.06
    POSITIVE LOGITS
    ube
    0.10
    Means
    0.10
    ioni
    0.10
    means
    0.10
    Īĺ
    0.10
     sä
    0.10
    LING
    0.10
     kort
    0.09
    ties
    0.09
     enorme
    0.09
    Activations Density 0.006%

    No Known Activations