© 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. 55141
    Prev
    Next
    INDEX
    Explanations

    exclusive license or features

    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
    anela
    -0.09
    lage
    -0.08
     Combo
    -0.08
    uw
    -0.08
     Finished
    -0.08
    ore
    -0.07
     WALL
    -0.07
    odate
    -0.07
    comb
    -0.07
    otta
    -0.07
    POSITIVE LOGITS
    ctl
    0.10
     evenings
    0.09
    ral
    0.09
    atham
    0.09
     yourselves
    0.09
     Aren
    0.09
     WWW
    0.09
     sensible
    0.09
     Yourself
    0.09
    /trans
    0.08
    Activations Density 0.001%

    No Known Activations