© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 56176
    Prev
    Next
    INDEX
    Explanations

    study, tour, game, course details

    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
    malink
    -0.10
    anje
    -0.09
    loh
    -0.09
    acer
    -0.09
    enville
    -0.09
    qli
    -0.09
     mannen
    -0.09
     Concord
    -0.08
    ucs
    -0.08
    ENU
    -0.08
    POSITIVE LOGITS
    comm
    0.09
     spo
    0.09
    è²
    0.08
    Amb
    0.08
     Docs
    0.08
    -pres
    0.08
     others
    0.07
    ambi
    0.07
    "."
    0.07
    Spy
    0.07
    Activations Density 0.004%

    No Known Activations