© 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. 57219
    Prev
    Next
    INDEX
    Explanations

    paths with slashes and `/lists` or `projects`

    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
    ama
    -0.10
    noon
    -0.10
    ivia
    -0.09
     Warp
    -0.09
    neas
    -0.09
     linen
    -0.09
    097
    -0.09
    ières
    -0.09
    ACS
    -0.09
    anged
    -0.08
    POSITIVE LOGITS
    cheon
    0.07
    ige
    0.07
    eva
    0.07
     Zuk
    0.07
    gos
    0.07
    fo
    0.07
    .ut
    0.07
    CAC
    0.07
    cus
    0.07
    /unit
    0.07
    Activations Density 0.002%

    No Known Activations