© 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. 29984
    Prev
    Next
    INDEX
    Explanations

    "ar" suffix or prefix, or "TAR"

    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
    eer
    -0.11
    ë¡Ŀ
    -0.10
    rand
    -0.10
    gear
    -0.10
    MAS
    -0.10
    aires
    -0.10
    epar
    -0.10
    ary
    -0.10
    ess
    -0.10
    र
    -0.10
    POSITIVE LOGITS
    bitrary
    0.14
    ithmetic
    0.13
    beiten
    0.13
    beiter
    0.13
    riers
    0.13
    abouts
    0.13
    rier
    0.12
    ACTER
    0.12
    bage
    0.12
    red
    0.12
    Activations Density 0.384%

    No Known Activations