© 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. 61574
    Prev
    Next
    INDEX
    Explanations

    works for, plays for

    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
    enco
    -0.10
    -rad
    -0.10
    ussed
    -0.10
    allen
    -0.09
    riott
    -0.09
    anan
    -0.09
    cef
    -0.09
    elight
    -0.09
     Pap
    -0.09
    tok
    -0.09
    POSITIVE LOGITS
    (ed
    0.12
    erva
    0.09
     nowhere
    0.09
     Marin
    0.07
    cstdint
    0.06
    (es
    0.06
    ux
    0.06
     currently
    0.06
     loot
    0.06
     allegiance
    0.06
    Activations Density 0.107%

    No Known Activations