© 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. 112288
    Prev
    Next
    INDEX
    Explanations

    history of human civilization

    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
     Unicorn
    -0.07
     Widow
    -0.07
    aeda
    -0.07
     familiar
    -0.07
    umber
    -0.07
     strt
    -0.07
    iny
    -0.06
    ambi
    -0.06
    inz
    -0.06
    amine
    -0.06
    POSITIVE LOGITS
     mankind
    0.26
     humanity
    0.20
     civilization
    0.18
    ankind
    0.18
     hum
    0.16
     history
    0.15
     science
    0.15
     humans
    0.15
     man
    0.14
     society
    0.14
    Activations Density 0.018%

    No Known Activations