© 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. 235
    Prev
    Next
    INDEX
    Explanations

    Lib, Col, lib

    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
    osate
    -0.12
    culate
    -0.11
    lectual
    -0.10
    ized
    -0.10
    istics
    -0.10
    velt
    -0.10
    antaged
    -0.10
    eer
    -0.10
    obic
    -0.09
    aysia
    -0.09
    POSITIVE LOGITS
    'l
    0.11
    iton
    0.10
    ig
    0.10
    ag
    0.09
    ri
    0.09
    ac
    0.09
    el
    0.09
    ut
    0.09
    é
    0.09
    il
    0.09
    Activations Density 5.187%

    No Known Activations