© 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. 55332
    Prev
    Next
    INDEX
    Explanations

    damage and health stats

    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
    ober
    -0.08
     Murdoch
    -0.08
    nap
    -0.08
     Marian
    -0.08
     Grant
    -0.08
     fuel
    -0.08
     Solomon
    -0.08
    atal
    -0.08
     apt
    -0.08
     aria
    -0.08
    POSITIVE LOGITS
    ansen
    0.09
    utive
    0.09
     inflicted
    0.09
     Vaugh
    0.09
    agrant
    0.09
     multim
    0.08
    pson
    0.08
     Pais
    0.08
     Backend
    0.08
     graz
    0.08
    Activations Density 0.011%

    No Known Activations