© 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. 1229
    Prev
    Next
    INDEX
    Explanations

    camera shake, lung regions, display traces, enterprise computing, steel making, squash family, call center system, brain chromatin, convertible top, aflatoxin

    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
    chu
    -0.08
     Gross
    -0.07
     obs
    -0.07
     Stefan
    -0.07
    efa
    -0.07
    -heavy
    -0.07
     Glad
    -0.07
    ipa
    -0.07
     displ
    -0.06
    ollar
    -0.06
    POSITIVE LOGITS
    -specific
    0.11
    -wide
    0.11
    wide
    0.09
    Wide
    0.09
     Kah
    0.08
    -owned
    0.08
    -grade
    0.08
    sky
    0.08
    nero
    0.08
    .gov
    0.08
    Activations Density 3.062%

    No Known Activations