© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 89759
    Prev
    Next
    INDEX
    Explanations

    relax or relax after

    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
    nde
    -0.10
     Sey
    -0.10
     busy
    -0.10
     Vernon
    -0.10
    sek
    -0.10
    alion
    -0.10
     amet
    -0.09
     Ellis
    -0.09
     conjug
    -0.09
     Ere
    -0.09
    POSITIVE LOGITS
     noticeably
    0.16
     considerably
    0.16
     slightly
    0.16
     visibly
    0.14
     significantly
    0.14
     gradually
    0.12
     grip
    0.12
     markedly
    0.12
     meas
    0.11
    ensch
    0.11
    Activations Density 0.006%

    No Known Activations