© 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. 54950
    Prev
    Next
    INDEX
    Explanations

    HTML/wiki markup attributes

    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
     [...
    -0.07
    algorithm
    -0.07
     lets
    -0.07
     elev
    -0.07
     ashes
    -0.07
     Robotics
    -0.06
     intellig
    -0.06
     briefly
    -0.06
     e
    -0.06
    SG
    -0.06
    POSITIVE LOGITS
    irc
    0.11
    bung
    0.11
    ế
    0.11
     buckle
    0.11
    ave
    0.10
    itionally
    0.10
     collaps
    0.10
    ë¦Ħ
    0.10
     inval
    0.10
    IRC
    0.10
    Activations Density 0.012%

    No Known Activations