© 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. 56658
    Prev
    Next
    INDEX
    Explanations

    end of clause or phrase

    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
    elper
    -0.08
     worse
    -0.07
    =end
    -0.07
    fid
    -0.07
     tslint
    -0.07
    _->
    -0.07
    entic
    -0.07
    mapper
    -0.07
     unveiled
    -0.06
     worst
    -0.06
    POSITIVE LOGITS
     ideally
    0.10
    éĻ¤
    0.10
     likely
    0.09
     presumably
    0.09
     Likely
    0.09
     proceeding
    0.09
    spa
    0.09
    mes
    0.09
    ity
    0.09
     presumed
    0.09
    Activations Density 0.022%

    No Known Activations