© 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. 4519
    Prev
    Next
    INDEX
    Explanations

    check to see if

    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
     backstage
    -0.08
     Buck
    -0.07
     Dana
    -0.07
    uhl
    -0.07
    illi
    -0.07
     cep
    -0.07
     Stamina
    -0.07
     caul
    -0.07
     coherence
    -0.06
    elle
    -0.06
    POSITIVE LOGITS
    -marker
    0.10
    aira
    0.09
    isp
    0.09
    qua
    0.09
    ugo
    0.09
     rent
    0.09
    -vers
    0.09
     contenders
    0.09
     sext
    0.09
    osa
    0.09
    Activations Density 0.796%

    No Known Activations