© 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. 58319
    Prev
    Next
    INDEX
    Explanations

    of brain, blood, cellular, myocardial

    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
     extinction
    -0.10
    bled
    -0.09
     spir
    -0.09
    ference
    -0.09
     overdose
    -0.09
    dac
    -0.08
    arth
    -0.08
    ä¼
    -0.08
    isters
    -0.08
    irth
    -0.08
    POSITIVE LOGITS
     unp
    0.11
     backstage
    0.09
    æ´»
    0.09
     parc
    0.09
     ongoing
    0.09
     apro
    0.08
    -active
    0.08
     disturbed
    0.08
    ximity
    0.08
     Guil
    0.08
    Activations Density 0.051%

    No Known Activations