© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 5035
    Prev
    Next
    INDEX
    Explanations

    time, duration, half-life

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Maxim
    -0.10
     Mich
    -0.09
    Mich
    -0.08
    875
    -0.08
    illion
    -0.08
     pymysql
    -0.08
    flags
    -0.08
     Dump
    -0.07
    $č↵
    -0.07
     highest
    -0.07
    POSITIVE LOGITS
     duration
    0.38
     durations
    0.36
     shortest
    0.31
     Duration
    0.30
     elapsed
    0.30
    duration
    0.28
    Duration
    0.28
     shorter
    0.27
     timeframe
    0.27
     longest
    0.26
    Activations Density 0.882%

    No Known Activations