© 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. 3282
    Prev
    Next
    INDEX
    Explanations

    defined as either

    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
    ellas
    -0.08
    UT
    -0.07
    UC
    -0.07
     HL
    -0.07
     levels
    -0.07
     Survey
    -0.07
    vey
    -0.07
     Analy
    -0.06
     various
    -0.06
     religious
    -0.06
    POSITIVE LOGITS
     EITHER
    0.18
    Either
    0.14
     either
    0.14
     Either
    0.13
     atleast
    0.13
     preferably
    0.13
     unequiv
    0.13
     âī¥
    0.12
    either
    0.12
     verified
    0.11
    Activations Density 0.176%

    No Known Activations