© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 2321
    Prev
    Next
    INDEX
    Explanations

    action, activity, status, or state

    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
     convin
    -0.08
    rust
    -0.08
    orem
    -0.08
     marché
    -0.08
     clearing
    -0.08
     marathon
    -0.08
    unque
    -0.08
     System
    -0.08
     Scr
    -0.08
    uld
    -0.08
    POSITIVE LOGITS
    Certain
    0.10
    æŁ
    0.10
    —for
    0.10
     certain
    0.10
     Certain
    0.09
    Something
    0.09
     Duncan
    0.09
    /by
    0.09
     something
    0.09
     continua
    0.09
    Activations Density 0.747%

    No Known Activations