© 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. 1458
    Prev
    Next
    INDEX
    Explanations

    conjunctions and sentence transitions

    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
     Somebody
    -0.11
     Couldn
    -0.11
     Yours
    -0.11
     Oops
    -0.10
    å¥
    -0.09
     Unsure
    -0.09
     Stuff
    -0.09
    Everybody
    -0.09
     Everybody
    -0.09
     Looks
    -0.09
    POSITIVE LOGITS
     Additionally
    0.18
     additionally
    0.17
     However
    0.15
     Furthermore
    0.15
    Additionally
    0.14
     moreover
    0.14
     furthermore
    0.14
     however
    0.13
    However
    0.13
     Moreover
    0.12
    Activations Density 1.736%

    No Known Activations