© 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. 56358
    Prev
    Next
    INDEX
    Explanations

    DVD

    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
    ning
    -0.11
    uem
    -0.11
     cons
    -0.10
    ely
    -0.10
    tle
    -0.10
    oral
    -0.09
     numb
    -0.09
    ional
    -0.09
    .repeat
    -0.09
    uesta
    -0.09
    POSITIVE LOGITS
    er
    0.08
    cca
    0.08
    ead
    0.08
    .EXIT
    0.08
    iful
    0.07
    erer
    0.07
    ows
    0.07
    au
    0.07
    creen
    0.07
    las
    0.07
    Activations Density 0.003%

    No Known Activations