© 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. 57048
    Prev
    Next
    INDEX
    Explanations

    Prophet Muhammad

    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
    thood
    -0.11
    ehr
    -0.10
    tg
    -0.10
    agram
    -0.09
    tz
    -0.09
    ardi
    -0.08
    appable
    -0.08
    loth
    -0.08
    erable
    -0.08
    indy
    -0.08
    POSITIVE LOGITS
     Redistribution
    0.09
     distant
    0.09
     br
    0.09
     fle
    0.09
     Garrison
    0.09
    conditions
    0.09
    ãĥ¼ãĤ
    0.09
     Mission
    0.09
     flashback
    0.09
     Aer
    0.08
    Activations Density 0.006%

    No Known Activations