© 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. 1604
    Prev
    Next
    INDEX
    Explanations

    entirely, solely, exclusively

    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
     pertinent
    -0.12
     requisite
    -0.11
     relevant
    -0.10
     sizable
    -0.10
    atta
    -0.10
    agi
    -0.09
     =================================================================================
    -0.09
    misc
    -0.09
    atz
    -0.09
    persistent
    -0.09
    POSITIVE LOGITS
     primarily
    0.20
     exclusively
    0.19
     solely
    0.18
     entirely
    0.18
     only
    0.18
     strictly
    0.17
     mainly
    0.17
     predominantly
    0.16
     mostly
    0.16
     purely
    0.15
    Activations Density 3.106%

    No Known Activations