© 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. 17767
    Prev
    Next
    INDEX
    Explanations

    fresh or refreshing

    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
     humiliating
    -0.11
     slit
    -0.10
    Toolkit
    -0.10
    undler
    -0.10
    /nav
    -0.09
    /cop
    -0.09
    endi
    -0.09
     leisure
    -0.09
     Habit
    -0.09
    ippy
    -0.09
    POSITIVE LOGITS
     refreshing
    0.48
     fresh
    0.46
     refresh
    0.40
     freshness
    0.39
     Refresh
    0.36
     Fresh
    0.36
    fresh
    0.35
     fres
    0.34
     refreshed
    0.32
    refresh
    0.30
    Activations Density 0.264%

    No Known Activations