© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 56422
    Prev
    Next
    INDEX
    Explanations

    date labels

    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
    nar
    -0.08
    enticate
    -0.07
     Atlas
    -0.07
    ê
    -0.07
     Cyr
    -0.07
    ensa
    -0.07
     Fay
    -0.07
     Antonio
    -0.06
    chain
    -0.06
     closed
    -0.06
    POSITIVE LOGITS
     millenn
    0.10
    /preferences
    0.10
    обÑĭ
    0.10
    öffent
    0.10
    ureau
    0.10
    ?):
    0.09
    mite
    0.09
    Preview
    0.09
    TRA
    0.09
    erg
    0.09
    Activations Density 0.001%

    No Known Activations