© 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. 56289
    Prev
    Next
    INDEX
    Explanations

    citation bracket numbers

    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
     misunder
    -0.09
    Abb
    -0.07
     vac
    -0.07
     neatly
    -0.07
     mutually
    -0.07
     turf
    -0.07
     Credentials
    -0.07
     odds
    -0.07
     Nic
    -0.07
     medic
    -0.07
    POSITIVE LOGITS
     wand
    0.09
    alla
    0.09
     CE
    0.09
     oral
    0.09
    ya
    0.09
     witness
    0.09
    ém
    0.09
    weg
    0.09
    zan
    0.09
     wakes
    0.09
    Activations Density 0.014%

    No Known Activations