© 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. 29776
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Rach
    -0.10
    adb
    -0.09
    engl
    -0.08
    nam
    -0.08
     Inquiry
    -0.08
    /team
    -0.08
     suff
    -0.08
    HCI
    -0.08
    UIS
    -0.08
    egg
    -0.07
    POSITIVE LOGITS
     educators
    0.10
     INT
    0.09
    avana
    0.09
     Eh
    0.09
     treasures
    0.09
    structor
    0.09
     firsthand
    0.09
    ugen
    0.09
     hal
    0.09
     intention
    0.09
    Activations Density 0.000%

    No Known Activations