© 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. 54418
    Prev
    Next
    INDEX
    Explanations

    divorce

    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
    hin
    -0.09
     Lover
    -0.09
    Fra
    -0.08
     ë²
    -0.07
    hill
    -0.07
     dates
    -0.06
     dating
    -0.06
     bank
    -0.06
    chal
    -0.06
     YELLOW
    -0.06
    POSITIVE LOGITS
    ço
    0.11
    enticator
    0.11
    werk
    0.11
    idor
    0.10
    aug
    0.10
    hoot
    0.10
     Fairfield
    0.10
     Aires
    0.10
     Declarations
    0.10
    hub
    0.10
    Activations Density 0.002%

    No Known Activations