© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 15851
    Prev
    Next
    INDEX
    Explanations

    Ri followed by specific endings (e.g., -ordan, -e)

    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
    ãĤ§
    -0.10
    doc
    -0.10
    ë¡Ŀ
    -0.10
    icus
    -0.09
    lob
    -0.09
    oire
    -0.09
    ienen
    -0.09
    acad
    -0.09
    ÃŃt
    -0.09
    lore
    -0.09
    POSITIVE LOGITS
    ordan
    0.15
    ght
    0.11
    annon
    0.11
     ripe
    0.10
    ptide
    0.10
    issan
    0.10
    chie
    0.09
    emann
    0.09
    Aus
    0.09
    esses
    0.09
    Activations Density 0.041%

    No Known Activations