© 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. 58367
    Prev
    Next
    INDEX
    Explanations

    Ohio

    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
    IES
    -0.11
    phy
    -0.10
    MetaData
    -0.10
    -0.10
    annot
    -0.10
    .githubusercontent
    -0.10
    ched
    -0.10
     Humb
    -0.10
    queda
    -0.09
     Patt
    -0.09
    POSITIVE LOGITS
    ary
    0.09
    aire
    0.07
    ayo
    0.07
    asthan
    0.07
    stone
    0.07
    rink
    0.07
    rust
    0.07
     watch
    0.07
    an
    0.07
     Cyr
    0.06
    Activations Density 0.004%

    No Known Activations