© 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. 4070
    Prev
    Next
    INDEX
    Explanations

    Java serialization and versioning

    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
    alus
    -0.10
     cyl
    -0.10
     whe
    -0.09
    ckt
    -0.09
    occo
    -0.09
    andas
    -0.09
     meis
    -0.09
    eel
    -0.09
    Tube
    -0.09
    fee
    -0.09
    POSITIVE LOGITS
     Sept
    0.07
    UU
    0.07
     Pell
    0.07
    ens
    0.07
     sept
    0.07
    .comp
    0.07
    conti
    0.07
    rish
    0.06
     alcoholic
    0.06
    PerPage
    0.06
    Activations Density 0.001%

    No Known Activations