© 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. 8485
    Prev
    Next
    INDEX
    Explanations

    seeking help or solutions

    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
     Cru
    -0.08
    abr
    -0.08
     Chandler
    -0.08
    burgh
    -0.08
     distur
    -0.08
    wy
    -0.08
     ud
    -0.07
    ROC
    -0.07
    .super
    -0.07
    uced
    -0.07
    POSITIVE LOGITS
     solve
    0.10
    fant
    0.09
    ller
    0.09
    HELP
    0.09
    707
    0.09
     help
    0.09
    ãĢĤãĢĤ↵↵
    0.09
     still
    0.09
     alleviate
    0.09
     allev
    0.08
    Activations Density 0.238%

    No Known Activations