© 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. 91603
    Prev
    Next
    INDEX
    Explanations

    legal terms and conditions

    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
     Kota
    -0.10
     Hover
    -0.10
    onte
    -0.10
     pont
    -0.09
    Hover
    -0.09
    uble
    -0.09
     Ironically
    -0.09
    isch
    -0.09
     pil
    -0.09
     pom
    -0.08
    POSITIVE LOGITS
     fatt
    0.10
    thew
    0.10
    arak
    0.10
     awaits
    0.09
     Pee
    0.09
    715
    0.09
     peer
    0.09
     afterward
    0.09
     truly
    0.09
     await
    0.08
    Activations Density 0.001%

    No Known Activations