© 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. 58027
    Prev
    Next
    INDEX
    Explanations

    conditional logic: if, else if, case

    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
     successive
    -0.09
     jeune
    -0.09
    icens
    -0.09
    jac
    -0.09
    -www
    -0.09
    å±Ģ
    -0.08
     Till
    -0.08
     strategic
    -0.08
    adia
    -0.08
    dat
    -0.08
    POSITIVE LOGITS
    ente
    0.10
     Hum
    0.09
     anywhere
    0.09
     tas
    0.08
    ofi
    0.08
    licht
    0.08
    TA
    0.08
     neutral
    0.08
     leaks
    0.07
     rapp
    0.07
    Activations Density 0.013%

    No Known Activations