© 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. 1754
    Prev
    Next
    INDEX
    Explanations

    time of, time to, time span

    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
     timed
    -0.11
    _time
    -0.09
    _TIME
    -0.09
    -0.08
    _timer
    -0.08
    ness
    -0.08
    AMS
    -0.08
     spr
    -0.08
    sole
    -0.08
    ultiply
    -0.08
    POSITIVE LOGITS
    frames
    0.19
    -consuming
    0.18
    åĢ
    0.17
     spent
    0.17
     frame
    0.16
    frame
    0.15
    keeping
    0.15
    othy
    0.14
    lots
    0.14
    .sleep
    0.14
    Activations Density 0.504%

    No Known Activations