© 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. 114482
    Prev
    Next
    INDEX
    Explanations

    newness, new beginnings

    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
    oi
    -0.10
    uye
    -0.10
    amar
    -0.09
    JE
    -0.09
    UpperCase
    -0.09
     backstage
    -0.09
     sooner
    -0.09
    arty
    -0.09
    andi
    -0.09
     overhe
    -0.08
    POSITIVE LOGITS
     fresh
    0.55
     anew
    0.47
    fresh
    0.42
     Fresh
    0.41
     freshly
    0.39
    Fresh
    0.38
     freshness
    0.38
     new
    0.36
     virgin
    0.35
    -new
    0.33
    Activations Density 1.112%

    No Known Activations