© 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. 8458
    Prev
    Next
    INDEX
    Explanations

    java list initialization

    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
     ren
    -0.10
     cement
    -0.09
     Stap
    -0.09
    INAL
    -0.08
     ="";↵
    -0.08
     esp
    -0.08
    674
    -0.08
    eu
    -0.08
     Ast
    -0.08
    ipy
    -0.08
    POSITIVE LOGITS
     specialized
    0.14
     specialised
    0.12
     special
    0.11
     niche
    0.10
     specialty
    0.10
     specializes
    0.10
     specially
    0.09
    special
    0.09
     specialize
    0.09
     specials
    0.08
    Activations Density 0.111%

    No Known Activations