© 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. 54166
    Prev
    Next
    INDEX
    Explanations

    row, section, or index

    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
    .io
    -0.09
     spor
    -0.09
    graf
    -0.09
    ifax
    -0.09
     UPDATE
    -0.09
    apt
    -0.09
    wald
    -0.09
     Fence
    -0.08
     odd
    -0.08
    yo
    -0.08
    POSITIVE LOGITS
    rome
    0.08
    atten
    0.08
    PIC
    0.08
     ucwords
    0.08
    andler
    0.08
     emb
    0.08
    etta
    0.07
    eno
    0.07
     Patri
    0.07
     nowrap
    0.07
    Activations Density 0.004%

    No Known Activations