© 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. 57335
    Prev
    Next
    INDEX
    Explanations

    leaning or sitting positions

    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
     marin
    -0.09
     sleeps
    -0.09
    occer
    -0.09
    ibi
    -0.09
     âĸº
    -0.09
     Jar
    -0.09
     Decision
    -0.09
    marsh
    -0.09
    ior
    -0.09
     pat
    -0.09
    POSITIVE LOGITS
    -functions
    0.08
    oft
    0.08
     ethn
    0.08
    车
    0.08
    loc
    0.07
    izr
    0.07
    itzer
    0.07
    .maps
    0.07
     missionaries
    0.07
     regional
    0.06
    Activations Density 0.015%

    No Known Activations