© 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. 115724
    Prev
    Next
    INDEX
    Explanations

    political topics and dates

    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
    DIC
    -0.11
    ific
    -0.10
    dic
    -0.10
    ohn
    -0.10
     Tao
    -0.09
    istro
    -0.09
    unders
    -0.08
     Vulkan
    -0.08
     Buk
    -0.08
    iefs
    -0.08
    POSITIVE LOGITS
    —one
    0.10
    /a
    0.10
    lick
    0.09
    edo
    0.09
    yr
    0.09
     ``(
    0.09
    /dd
    0.09
    asu
    0.08
     Falk
    0.08
     unr
    0.08
    Activations Density 1.754%

    No Known Activations