© 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. 112742
    Prev
    Next
    INDEX
    Explanations

    analyze / analysis

    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
     Zw
    -0.12
    оказ
    -0.10
     Screening
    -0.09
     Checking
    -0.09
     dire
    -0.09
     demonstrations
    -0.09
    ollen
    -0.09
     introduce
    -0.09
    ä»ĭ
    -0.09
     reminding
    -0.09
    POSITIVE LOGITS
     dissect
    0.37
     analyzing
    0.36
     analys
    0.35
     analysis
    0.34
     analyze
    0.34
     analyzes
    0.34
     Analy
    0.33
    analyze
    0.31
     analytical
    0.31
     analyses
    0.31
    Activations Density 0.846%

    No Known Activations