© 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. 58589
    Prev
    Next
    INDEX
    Explanations

    US state or province abbreviations

    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
    pond
    -0.12
    isle
    -0.11
    allen
    -0.11
    emplates
    -0.10
     Wire
    -0.10
    Cycle
    -0.10
    /↵↵↵↵
    -0.10
    cycles
    -0.10
    aeda
    -0.10
    anzi
    -0.10
    POSITIVE LOGITS
    er
    0.08
     lic
    0.08
    ene
    0.07
    oo
    0.07
     clo
    0.07
     Stanton
    0.06
    ãģ£ãģ¦
    0.06
    'r
    0.06
     tame
    0.06
     vest
    0.06
    Activations Density 0.007%

    No Known Activations