© 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. 58382
    Prev
    Next
    INDEX
    Explanations

    exception occurrence

    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
    ington
    -0.09
    NESS
    -0.08
     Crush
    -0.08
    dez
    -0.08
    kal
    -0.08
     GK
    -0.08
    rans
    -0.08
    izo
    -0.07
    plen
    -0.07
    oger
    -0.07
    POSITIVE LOGITS
    eya
    0.11
    itty
    0.10
    esh
    0.10
    arie
    0.10
     romant
    0.10
    hips
    0.10
    eca
    0.10
    iros
    0.10
    lac
    0.09
     Revel
    0.09
    Activations Density 0.004%

    No Known Activations