© 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. 54784
    Prev
    Next
    INDEX
    Explanations

    finite field or sides

    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
    ummings
    -0.07
     globals
    -0.07
    505
    -0.07
     sensit
    -0.07
     pron
    -0.06
     Democr
    -0.06
     pam
    -0.06
     rend
    -0.06
    uffs
    -0.06
     brisk
    -0.06
    POSITIVE LOGITS
          ↵      ↵
    0.11
     Mojo
    0.11
     Gates
    0.10
    collapse
    0.10
    installer
    0.10
     Conn
    0.10
     fue
    0.09
    ÙĦا
    0.09
     die
    0.09
     rot
    0.09
    Activations Density 0.030%

    No Known Activations