© 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. 1394
    Prev
    Next
    INDEX
    Explanations

    conjunctions and clause separators

    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
     WITHOUT
    -0.10
     NOT
    -0.09
    CCCCCC
    -0.08
    WITHOUT
    -0.08
    .Maybe
    -0.08
     undeniable
    -0.08
     albeit
    -0.08
    wal
    -0.08
    /domain
    -0.08
    aud
    -0.08
    POSITIVE LOGITS
     nor
    0.41
     Nor
    0.33
    nor
    0.26
    Nor
    0.25
     Instead
    0.23
     anymore
    0.22
     instead
    0.21
    Instead
    0.20
     NOR
    0.19
     sondern
    0.17
    Activations Density 1.513%

    No Known Activations