© 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. 55238
    Prev
    Next
    INDEX
    Explanations

    Irish and Central European names

    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
    ave
    -0.09
    gne
    -0.09
    antic
    -0.09
    tica
    -0.08
    eler
    -0.08
    еÑĩ
    -0.08
    lite
    -0.08
    igram
    -0.08
    ior
    -0.08
    BJ
    -0.08
    POSITIVE LOGITS
    Ùij
    0.09
    stit
    0.09
    ed
    0.09
    /features
    0.08
    ties
    0.08
    ])]
    0.08
    way
    0.08
    in
    0.08
    ench
    0.08
    Pressed
    0.08
    Activations Density 0.010%

    No Known Activations