© 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. 112621
    Prev
    Next
    INDEX
    Explanations

    solstices and equinoxes

    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
    ipa
    -0.09
    hek
    -0.09
    ynes
    -0.09
     Island
    -0.09
     Mobil
    -0.09
    ioc
    -0.09
     Sting
    -0.09
    assi
    -0.08
     hopeful
    -0.08
     alike
    -0.08
    POSITIVE LOGITS
     refl
    0.10
     charisma
    0.09
     Kenny
    0.09
    avl
    0.09
    cts
    0.09
    baum
    0.09
     Lif
    0.09
    clinic
    0.09
    keypress
    0.09
    .bz
    0.09
    Activations Density 0.001%

    No Known Activations