© 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. 48625
    Prev
    Next
    INDEX
    Explanations

    the first

    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
    æľĢ
    -0.11
     æľĢ
    -0.11
    iest
    -0.10
     Thi
    -0.10
     happiest
    -0.10
    íĻĶ
    -0.09
     Kut
    -0.09
     Kl
    -0.09
    iams
    -0.09
     maxim
    -0.09
    POSITIVE LOGITS
     first
    0.30
    first
    0.22
     FIRST
    0.18
    	first
    0.18
    .first
    0.17
     пеÑĢв
    0.17
    (first
    0.16
     inaugural
    0.16
    _first
    0.15
     fist
    0.15
    Activations Density 0.363%

    No Known Activations