© 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. 3689
    Prev
    Next
    INDEX
    Explanations

    `(x` or number followed by `(x`

    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
    ^
    -0.17
    ^{
    -0.15
    ^[
    -0.15
    ^(
    -0.15
    ^{-
    -0.14
    ²
    -0.13
    ingly
    -0.12
    ^n
    -0.11
    ^\
    -0.11
    ela
    -0.10
    POSITIVE LOGITS
     Bett
    0.07
     capit
    0.07
     Hector
    0.07
    -mini
    0.07
    iterr
    0.07
    umin
    0.07
     Advent
    0.07
     entert
    0.06
    ult
    0.06
    voke
    0.06
    Activations Density 0.112%

    No Known Activations