© 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. 2825
    Prev
    Next
    INDEX
    Explanations

    expressions of amusement or disbelief

    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
    line
    -0.10
    lea
    -0.08
    ×ķ
    -0.08
     REALLY
    -0.08
     bankrupt
    -0.08
     waist
    -0.07
     Mens
    -0.07
    rea
    -0.07
     Pare
    -0.07
     hung
    -0.07
    POSITIVE LOGITS
     Teh
    0.12
     yay
    0.12
     DERP
    0.11
    orz
    0.11
     derp
    0.10
    undry
    0.10
     goodness
    0.10
     unto
    0.10
    (tm
    0.10
    butt
    0.10
    Activations Density 0.395%

    No Known Activations