© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 56138
    Prev
    Next
    INDEX
    Explanations

    blogs and logs

    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
     Petersburg
    -0.10
     bach
    -0.10
     Goose
    -0.09
     abort
    -0.09
    ocha
    -0.08
     aborted
    -0.08
     Pace
    -0.08
     Yankee
    -0.08
    alion
    -0.08
    imizer
    -0.08
    POSITIVE LOGITS
    ane
    0.09
     away
    0.08
    mand
    0.08
     Experiment
    0.08
    /default
    0.08
    аÑĤа
    0.08
     hearing
    0.08
    uckets
    0.08
     mand
    0.08
    aring
    0.08
    Activations Density 0.001%

    No Known Activations