© 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. 88441
    Prev
    Next
    INDEX
    Explanations

    done with / finished with

    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
    agr
    -0.10
     familiarity
    -0.10
    -produ
    -0.10
    ализ
    -0.10
     Typography
    -0.10
     Afterwards
    -0.10
     unfamiliar
    -0.10
    extension
    -0.10
     Measure
    -0.10
     bli
    -0.10
    POSITIVE LOGITS
     surprises
    0.13
     experimenting
    0.10
     forever
    0.09
     prelim
    0.09
     bothering
    0.08
     altogether
    0.08
     grieving
    0.08
    unning
    0.08
    aison
    0.08
    gan
    0.08
    Activations Density 0.009%

    No Known Activations