© 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. 930
    Prev
    Next
    INDEX
    Explanations

    up to

    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
     upright
    -0.10
     uphill
    -0.10
    lek
    -0.10
    Up
    -0.09
    nds
    -0.09
    ikan
    -0.09
    _up
    -0.09
     up
    -0.09
     upstairs
    -0.08
    _UP
    -0.08
    POSITIVE LOGITS
    /down
    0.24
    pers
    0.18
    draft
    0.15
    ping
    0.14
    ped
    0.14
    scaling
    0.14
    -front
    0.14
    vote
    0.13
    votes
    0.13
    river
    0.13
    Activations Density 0.475%

    No Known Activations