© 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. 2090
    Prev
    Next
    INDEX
    Explanations

    drug related terms

    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
    anton
    -0.09
    atin
    -0.09
    ally
    -0.09
    zap
    -0.08
    ipp
    -0.08
    ial
    -0.07
    rypton
    -0.07
     frag
    -0.07
    zens
    -0.07
    ebin
    -0.07
    POSITIVE LOGITS
    store
    0.13
    stores
    0.10
     bay
    0.10
    oi
    0.10
    coma
    0.09
    rev
    0.09
    oa
    0.09
    ster
    0.09
    buster
    0.09
    ger
    0.09
    Activations Density 0.094%

    No Known Activations