© 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. 30570
    Prev
    Next
    INDEX
    Explanations

    way or means

    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
     residue
    -0.10
    afort
    -0.10
     inaug
    -0.09
     dio
    -0.09
     Timing
    -0.09
     incompet
    -0.09
     compound
    -0.09
     impres
    -0.09
     requis
    -0.09
    agg
    -0.09
    POSITIVE LOGITS
     way
    0.23
     means
    0.16
     outlet
    0.16
     opportunity
    0.16
     form
    0.15
     exercise
    0.13
     Means
    0.13
     Outlet
    0.13
     fun
    0.13
     WAY
    0.13
    Activations Density 0.067%

    No Known Activations