© 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. 55796
    Prev
    Next
    INDEX
    Explanations

    repeating or ordinal counts

    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
     Fog
    -0.12
    /generated
    -0.09
    ffer
    -0.09
    ugu
    -0.09
    /ros
    -0.09
    igli
    -0.09
    asma
    -0.09
    ĻĤ
    -0.09
    lov
    -0.09
    zen
    -0.09
    POSITIVE LOGITS
     second
    0.17
     third
    0.17
     twice
    0.16
     repeated
    0.16
    第
    0.16
     Twice
    0.16
     repeat
    0.14
     finally
    0.14
     first
    0.13
     第
    0.13
    Activations Density 0.194%

    No Known Activations