© 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. 28769
    Prev
    Next
    INDEX
    Explanations

    `ULAR` suffixes

    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
     Bek
    -0.08
    linger
    -0.08
    /int
    -0.08
     bey
    -0.07
    able
    -0.07
     MacDonald
    -0.07
    -lite
    -0.07
     visiting
    -0.07
     Obt
    -0.07
     beck
    -0.07
    POSITIVE LOGITS
    ular
    0.11
    -même
    0.10
    unar
    0.10
     Pascal
    0.10
    ernen
    0.10
    Liked
    0.10
     impaired
    0.10
    oun
    0.10
    ivors
    0.10
    izontally
    0.10
    Activations Density 0.022%

    No Known Activations