© 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. 58330
    Prev
    Next
    INDEX
    Explanations

    US geographic locations and populations

    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
     aw
    -0.08
     tbody
    -0.08
     hum
    -0.07
    irit
    -0.07
     Dis
    -0.07
    FW
    -0.07
    pit
    -0.07
     Directorate
    -0.07
     succesfully
    -0.07
     und
    -0.07
    POSITIVE LOGITS
     Cummings
    0.13
    otope
    0.10
    acher
    0.10
    enne
    0.10
    kehr
    0.09
    bau
    0.09
    alic
    0.09
     Rockets
    0.09
     Cups
    0.09
    _den
    0.09
    Activations Density 0.105%

    No Known Activations