© 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. 88985
    Prev
    Next
    INDEX
    Explanations

    smooth movement and ease

    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
     Malk
    -0.11
     Extras
    -0.11
    aket
    -0.11
    aran
    -0.10
     Pom
    -0.10
     Saul
    -0.10
    udu
    -0.10
     exploded
    -0.10
     curled
    -0.10
     furnished
    -0.10
    POSITIVE LOGITS
     ease
    0.25
     smoothly
    0.24
     smooth
    0.23
     smoother
    0.22
     easier
    0.20
     glide
    0.20
     effortless
    0.20
    smooth
    0.19
     easy
    0.18
     Smooth
    0.18
    Activations Density 0.162%

    No Known Activations