© 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. 30519
    Prev
    Next
    INDEX
    Explanations

    for example or reasons

    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
    isin
    -0.11
    ritz
    -0.10
     clam
    -0.10
    jah
    -0.10
    ifix
    -0.09
    usi
    -0.09
     Idle
    -0.09
     Chancellor
    -0.09
     blot
    -0.09
     pine
    -0.09
    POSITIVE LOGITS
     reasons
    0.41
     Reasons
    0.40
     either
    0.35
    either
    0.30
     Either
    0.29
    Either
    0.26
     due
    0.25
    Reason
    0.24
     whatever
    0.24
     EITHER
    0.24
    Activations Density 1.032%

    No Known Activations