© 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. 3873
    Prev
    Next
    INDEX
    Explanations

    disease transmission, conditions, or prevention

    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
     rew
    -0.08
    ting
    -0.08
    ivia
    -0.07
     disease
    -0.07
    ween
    -0.07
    ium
    -0.07
    lia
    -0.07
    ter
    -0.07
    eti
    -0.06
     boxer
    -0.06
    POSITIVE LOGITS
     modele
    0.11
    mour
    0.11
    yk
    0.11
     mong
    0.10
    wide
    0.10
    ué
    0.10
     outbreak
    0.10
    ród
    0.10
    .AI
    0.10
    gressor
    0.10
    Activations Density 0.090%

    No Known Activations