© 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. 57488
    Prev
    Next
    INDEX
    Explanations

    workers' compensation

    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
    er
    -0.10
    æ´
    -0.10
     bell
    -0.10
     cred
    -0.10
    loon
    -0.09
    eman
    -0.09
    Ñģк
    -0.09
     marsh
    -0.09
     Circus
    -0.09
     Mem
    -0.09
    POSITIVE LOGITS
    aset
    0.10
     Pratt
    0.08
    cil
    0.08
    peria
    0.08
    oot
    0.08
    ahan
    0.08
    etter
    0.07
     Offices
    0.07
     soph
    0.07
    razier
    0.07
    Activations Density 0.002%

    No Known Activations