© 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. 18172
    Prev
    Next
    INDEX
    Explanations

    comparison with controls or norms

    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
    REAL
    -0.10
    etz
    -0.10
    ijo
    -0.09
     Nachricht
    -0.09
    urls
    -0.09
    iker
    -0.09
    -du
    -0.09
     Rounds
    -0.09
     impress
    -0.09
    ijn
    -0.09
    POSITIVE LOGITS
     average
    0.22
     averages
    0.22
     baseline
    0.20
     peers
    0.20
     benchmarks
    0.19
     benchmark
    0.19
     comparable
    0.18
     norms
    0.18
     norm
    0.17
     normal
    0.17
    Activations Density 1.368%

    No Known Activations