© 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. 54359
    Prev
    Next
    INDEX
    Explanations

    places and institutions

    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
     lodged
    -0.08
    egie
    -0.08
    bole
    -0.08
    afort
    -0.07
     Bast
    -0.07
     sage
    -0.07
     Misc
    -0.07
    stract
    -0.07
    /un
    -0.07
    usal
    -0.07
    POSITIVE LOGITS
     aide
    0.10
    еÑģÑĤв
    0.09
     Adams
    0.09
    =http
    0.09
     peril
    0.08
     restr
    0.08
    isl
    0.08
    hic
    0.08
    yal
    0.08
     deport
    0.08
    Activations Density 0.046%

    No Known Activations