© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 114839
    Prev
    Next
    INDEX
    Explanations

    speculative or uncertain outcomes

    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
     misd
    -0.12
     misunderstanding
    -0.12
     misunderstood
    -0.12
     misconception
    -0.12
     miscon
    -0.12
     misunderstand
    -0.11
    forget
    -0.11
     redundant
    -0.11
     selfish
    -0.11
     misunder
    -0.10
    POSITIVE LOGITS
     speculative
    0.25
     speculation
    0.22
     cautious
    0.20
     uncertainty
    0.19
     caution
    0.18
     uncertain
    0.18
     uncertainties
    0.18
     cautioned
    0.18
     Spec
    0.17
     speculate
    0.17
    Activations Density 0.378%

    No Known Activations