© 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. 3215
    Prev
    Next
    INDEX
    Explanations

    spatial conjunction "and"

    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
    hn
    -0.11
    abile
    -0.10
    utter
    -0.10
    locator
    -0.10
    itz
    -0.10
    rias
    -0.10
    unch
    -0.09
    UNK
    -0.09
    osen
    -0.09
     ako
    -0.09
    POSITIVE LOGITS
     region
    0.09
     surroundings
    0.08
    arena
    0.08
     vicinity
    0.08
     beyond
    0.08
     elsewhere
    0.08
     realm
    0.08
     surrounding
    0.08
     corners
    0.08
     abdomen
    0.08
    Activations Density 0.486%

    No Known Activations