© 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. 116215
    Prev
    Next
    INDEX
    Explanations

    Muhammad, prophet, messenger

    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
    vak
    -0.11
    ADM
    -0.11
    apia
    -0.10
     Mum
    -0.10
     Turkey
    -0.10
     fishes
    -0.10
     Gros
    -0.09
     volt
    -0.09
    Pont
    -0.09
     IDR
    -0.09
    POSITIVE LOGITS
     Messenger
    0.15
     Prophet
    0.13
     revelations
    0.13
     messenger
    0.12
     Arabia
    0.12
     Medina
    0.12
     prophet
    0.12
     revelation
    0.12
     MU
    0.11
     Muhammad
    0.11
    Activations Density 0.119%

    No Known Activations