© 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. 15568
    Prev
    Next
    INDEX
    Explanations

    broadband, broadcaster, broad-based, Broad Institute

    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
    åĵģ
    -0.10
     Rope
    -0.10
    amic
    -0.10
    ilian
    -0.10
    ouro
    -0.10
    apro
    -0.09
    imat
    -0.09
    ados
    -0.09
    ombo
    -0.09
     contro
    -0.08
    POSITIVE LOGITS
    ening
    0.27
    ened
    0.26
    sheets
    0.21
    sheet
    0.20
    sword
    0.19
    est
    0.19
    -strokes
    0.17
    scale
    0.16
    side
    0.16
     strokes
    0.15
    Activations Density 0.026%

    No Known Activations