© 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. 28093
    Prev
    Next
    INDEX
    Explanations

    performing tricks

    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
     forcibly
    -0.11
     noisy
    -0.10
     Cummings
    -0.10
     forced
    -0.10
     slugg
    -0.10
     sore
    -0.10
     fatt
    -0.10
     Rough
    -0.10
    forc
    -0.10
     rough
    -0.10
    POSITIVE LOGITS
     effortlessly
    0.16
     impress
    0.16
     seamlessly
    0.15
     tricks
    0.15
     perfectly
    0.15
     spinning
    0.14
    flip
    0.14
     gracefully
    0.14
     flipping
    0.14
     flips
    0.14
    Activations Density 0.156%

    No Known Activations