© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 8596
    Prev
    Next
    INDEX
    Explanations

    location and physical spaces

    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
    gov
    -0.07
    ogo
    -0.07
    jian
    -0.07
     brake
    -0.07
    Constraints
    -0.07
     restraint
    -0.06
     brakes
    -0.06
     pesos
    -0.06
     bystand
    -0.06
    Compat
    -0.06
    POSITIVE LOGITS
     headquarters
    0.14
     location
    0.12
     HQ
    0.12
     offices
    0.12
     downtown
    0.12
     dedicated
    0.11
     permanently
    0.11
     bases
    0.11
     locations
    0.11
     office
    0.11
    Activations Density 0.321%

    No Known Activations