© 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. 55091
    Prev
    Next
    INDEX
    Explanations

    In this paper

    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
    sville
    -0.10
     AUTHOR
    -0.09
     Ink
    -0.09
     soll
    -0.09
     mult
    -0.08
    ??↵↵
    -0.08
     prere
    -0.08
    AT
    -0.08
    —that
    -0.08
     Roland
    -0.08
    POSITIVE LOGITS
    antic
    0.09
     convention
    0.09
     spelling
    0.08
    idad
    0.08
    cour
    0.08
    ummer
    0.08
    orm
    0.08
     Terraria
    0.08
    ETHER
    0.08
    ormal
    0.07
    Activations Density 0.172%

    No Known Activations