© 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. 15450
    Prev
    Next
    INDEX
    Explanations

    critical concepts and analysis

    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
    asan
    -0.09
    eration
    -0.09
    esen
    -0.08
    edly
    -0.08
    ILI
    -0.08
     considerable
    -0.08
     retreat
    -0.08
     desperate
    -0.08
     supreme
    -0.08
     staple
    -0.08
    POSITIVE LOGITS
     acclaimed
    0.22
     acclaim
    0.20
    icism
    0.15
    -thinking
    0.13
    ically
    0.13
    ique
    0.12
    éri
    0.12
    sel
    0.11
    ity
    0.11
    tur
    0.11
    Activations Density 0.050%

    No Known Activations