© 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. 58171
    Prev
    Next
    INDEX
    Explanations

    code block delimiters or special characters

    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
    ogi
    -0.10
    uat
    -0.10
    estate
    -0.10
     mots
    -0.10
     cps
    -0.10
    ilters
    -0.10
    .ta
    -0.10
    ';↵↵↵↵
    -0.10
     Cro
    -0.10
    egot
    -0.10
    POSITIVE LOGITS
    éĻ¤
    0.08
    ori
    0.08
    ster
    0.07
    oro
    0.07
     absent
    0.07
     unseen
    0.07
    idia
    0.07
    tram
    0.06
     cohort
    0.06
     sequentially
    0.06
    Activations Density 0.001%

    No Known Activations