© 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. 1287
    Prev
    Next
    INDEX
    Explanations

    names followed by 's or longer forms

    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
    swick
    -0.10
    blem
    -0.10
    .IsNullOr
    -0.09
     trot
    -0.09
    į
    -0.09
    =function
    -0.09
    asher
    -0.09
    orget
    -0.09
    usp
    -0.09
     Glover
    -0.09
    POSITIVE LOGITS
    —who
    0.14
    -san
    0.11
     himself
    0.09
    's
    0.09
     Sr
    0.08
     pil
    0.08
     Wing
    0.08
    ’s
    0.07
     chronic
    0.07
    ´s
    0.07
    Activations Density 0.562%

    No Known Activations