© 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. 17757
    Prev
    Next
    INDEX
    Explanations

    like other examples

    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
     Hedge
    -0.10
     cach
    -0.09
     Padding
    -0.09
    enger
    -0.09
    562
    -0.09
    du
    -0.09
    cho
    -0.09
    collections
    -0.08
     outweigh
    -0.08
    ether
    -0.08
    POSITIVE LOGITS
     Toro
    0.12
     etwa
    0.10
     matrimon
    0.10
     ours
    0.09
    iec
    0.09
     Tinder
    0.09
     heav
    0.09
     newer
    0.09
     ones
    0.09
    iek
    0.09
    Activations Density 0.050%

    No Known Activations