© 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. 114232
    Prev
    Next
    INDEX
    Explanations

    making assumptions or statements

    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
     unfortunately
    -0.10
     unfortunate
    -0.10
     rightfully
    -0.09
     dep
    -0.09
     unfairly
    -0.09
    elah
    -0.09
     savvy
    -0.08
     Suit
    -0.08
     sadly
    -0.08
     appropriately
    -0.08
    POSITIVE LOGITS
     trusting
    0.12
     Forgot
    0.12
     hoping
    0.12
    omo
    0.12
     forgot
    0.12
     believe
    0.11
    ery
    0.11
     predictable
    0.11
     assume
    0.11
     expecting
    0.11
    Activations Density 0.050%

    No Known Activations