© 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. 55039
    Prev
    Next
    INDEX
    Explanations

    then action

    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
     sense
    -0.08
     domin
    -0.07
     right
    -0.07
    at
    -0.07
    hoot
    -0.07
    AGR
    -0.07
     Vac
    -0.07
     Wise
    -0.07
     Obtain
    -0.07
    cho
    -0.07
    POSITIVE LOGITS
    axon
    0.10
    ynes
    0.10
     otherwise
    0.10
     aggressively
    0.09
    avar
    0.09
    yscale
    0.09
    rats
    0.09
    mts
    0.09
    istr
    0.09
    flag
    0.09
    Activations Density 0.095%

    No Known Activations