© 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. 479
    Prev
    Next
    INDEX
    Explanations

    best kind cool solution option

    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
    existent
    -0.09
     progress
    -0.08
    uli
    -0.08
     pudd
    -0.07
     Fact
    -0.07
    ria
    -0.07
     Shields
    -0.07
    BB
    -0.07
    %(
    -0.07
     those
    -0.07
    POSITIVE LOGITS
     same
    0.23
     equivalent
    0.17
     SAME
    0.17
    same
    0.17
     Same
    0.15
     opposite
    0.14
    Same
    0.13
     least
    0.13
     necessary
    0.13
     même
    0.13
    Activations Density 1.452%

    No Known Activations