© 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. 1425
    Prev
    Next
    INDEX
    Explanations

    names of people or things

    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
     others
    -0.07
     yourselves
    -0.06
     enact
    -0.06
     Others
    -0.06
     dig
    -0.06
     Est
    -0.06
     Bale
    -0.06
    foil
    -0.06
     Ku
    -0.06
     ourselves
    -0.05
    POSITIVE LOGITS
     he
    0.17
     she
    0.15
     him
    0.14
    ä»ĸ
    0.13
     он
    0.12
    she
    0.12
    acre
    0.11
    he
    0.10
    /pass
    0.10
    Opts
    0.10
    Activations Density 1.822%

    No Known Activations