© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 56335
    Prev
    Next
    INDEX
    Explanations

    beyond scope and boundaries

    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
     afterward
    -0.11
     nonetheless
    -0.10
     thereafter
    -0.10
     afterwards
    -0.10
    æĮī
    -0.09
    ocrat
    -0.09
     вÑĭ
    -0.09
     occup
    -0.09
     upt
    -0.09
     upstairs
    -0.09
    POSITIVE LOGITS
     scope
    0.12
     confines
    0.12
     bounds
    0.11
     mere
    0.11
    _scope
    0.10
     realms
    0.10
     realm
    0.10
     boundaries
    0.09
     norm
    0.09
     limits
    0.09
    Activations Density 0.041%

    No Known Activations