© 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. 54161
    Prev
    Next
    INDEX
    Explanations

    boyfriend/girlfriend roles

    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
     wife
    -0.11
     wives
    -0.09
    keys
    -0.09
     neighbor
    -0.09
     intimacy
    -0.09
     flag
    -0.09
     bonding
    -0.08
     Wiley
    -0.08
     internally
    -0.08
     neighbors
    -0.08
    POSITIVE LOGITS
    pper
    0.09
     MSE
    0.08
    alf
    0.08
     Lola
    0.08
    /h
    0.08
    enden
    0.08
    udu
    0.08
    æĶ¶
    0.08
     Sammy
    0.08
     vacc
    0.08
    Activations Density 0.022%

    No Known Activations