© 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. 46509
    Prev
    Next
    INDEX
    Explanations

    variation, unevenness, irregularity

    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
    /rules
    -0.09
     punct
    -0.09
     grounded
    -0.09
    tdown
    -0.09
    /full
    -0.08
     finances
    -0.08
     cod
    -0.08
     Mund
    -0.08
     reinforcements
    -0.08
     Savage
    -0.08
    POSITIVE LOGITS
     uneven
    0.32
     irregular
    0.32
     variations
    0.28
     slight
    0.27
     variation
    0.26
     imperfect
    0.25
     inconsistencies
    0.25
     deviations
    0.25
     asym
    0.25
     Variation
    0.25
    Activations Density 0.585%

    No Known Activations