© 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. 4079
    Prev
    Next
    INDEX
    Explanations

    legal document closing phrases

    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
    —but
    -0.12
     seldom
    -0.10
     scarcely
    -0.10
     striking
    -0.09
     Arb
    -0.09
    oe
    -0.09
    —for
    -0.09
    rod
    -0.08
    aux
    -0.08
     echoing
    -0.08
    POSITIVE LOGITS
     hereby
    0.19
     herein
    0.14
     aforementioned
    0.13
     pursuant
    0.12
     thereof
    0.12
     said
    0.12
     persons
    0.11
    .Please
    0.11
     therein
    0.11
     presently
    0.11
    Activations Density 0.078%

    No Known Activations