© 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. 54090
    Prev
    Next
    INDEX
    Explanations

    mind's eye, senses, talent, touch

    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
    uma
    -0.11
    ãĤĪ
    -0.09
    '↵↵↵↵
    -0.09
    Serialized
    -0.09
     bro
    -0.09
    eu
    -0.09
    inery
    -0.09
    .appspot
    -0.09
     woll
    -0.09
     hardness
    -0.09
    POSITIVE LOGITS
    elin
    0.08
     Mil
    0.07
     pred
    0.07
    stack
    0.07
    erras
    0.07
    —with
    0.06
     Ple
    0.06
    display
    0.06
     Brisbane
    0.06
    \:
    0.06
    Activations Density 0.250%

    No Known Activations