© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 56760
    Prev
    Next
    INDEX
    Explanations

    oath, sworn, swear

    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
    concert
    -0.09
     agreed
    -0.09
     conc
    -0.08
     perm
    -0.07
    emin
    -0.07
    Past
    -0.07
    URITY
    -0.07
    ornment
    -0.07
    obody
    -0.07
    alo
    -0.07
    POSITIVE LOGITS
     oath
    0.10
     Taken
    0.10
    646
    0.09
    bee
    0.09
    kre
    0.09
    éķ
    0.09
     Toilet
    0.09
     swore
    0.09
     swear
    0.09
    ongs
    0.09
    Activations Density 0.005%

    No Known Activations