© 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. 112865
    Prev
    Next
    INDEX
    Explanations

    day numbers

    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
     Monday
    -0.16
    mond
    -0.15
    mon
    -0.14
    Monday
    -0.14
     Monroe
    -0.13
    -mon
    -0.13
     mono
    -0.13
     Mono
    -0.12
    Mono
    -0.12
     mon
    -0.12
    POSITIVE LOGITS
     Fri
    0.10
     Friday
    0.09
     Th
    0.09
     Thi
    0.09
     throm
    0.08
     hurricane
    0.08
    -th
    0.08
     whe
    0.08
     Genome
    0.08
     throttle
    0.08
    Activations Density 0.100%

    No Known Activations