© 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. 55326
    Prev
    Next
    INDEX
    Explanations

    incorporated by reference

    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
    elay
    -0.10
     compromised
    -0.09
     Gate
    -0.09
     McCorm
    -0.09
    appName
    -0.09
    Dar
    -0.09
     McM
    -0.08
    edral
    -0.08
     postpon
    -0.08
     retreat
    -0.08
    POSITIVE LOGITS
     Bib
    0.09
     CSA
    0.08
     Francis
    0.08
     bord
    0.08
    ornings
    0.08
     voices
    0.08
    assandra
    0.08
    uma
    0.07
    enate
    0.07
     peaked
    0.07
    Activations Density 0.006%

    No Known Activations