© 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-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 48558
    Prev
    Next
    INDEX
    Explanations

    into [time period/noun phrase]

    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
     entirety
    -0.10
    uling
    -0.10
     entire
    -0.09
     Gus
    -0.09
     scales
    -0.09
     aid
    -0.08
    olon
    -0.08
     Coco
    -0.08
    atis
    -0.08
     stopping
    -0.08
    POSITIVE LOGITS
    fter
    0.12
     journey
    0.11
     adulthood
    0.11
     Journey
    0.11
     tenure
    0.10
     Massive
    0.10
    à¸ģาร
    0.10
    meld
    0.10
    zek
    0.10
    -duration
    0.10
    Activations Density 0.052%

    No Known Activations