© 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. 15715
    Prev
    Next
    INDEX
    Explanations

    uncertainty about a state or behavior

    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
     probably
    -0.24
    Probably
    -0.18
     likely
    -0.18
     Probably
    -0.18
    probably
    -0.17
     apparently
    -0.15
    likely
    -0.15
     presumably
    -0.15
     often
    -0.14
     undoubtedly
    -0.14
    POSITIVE LOGITS
     somehow
    0.26
     simply
    0.21
     truly
    0.16
     secretly
    0.16
     unwitting
    0.15
     actually
    0.15
     doomed
    0.15
     merely
    0.15
     Simply
    0.14
     genuinely
    0.14
    Activations Density 0.261%

    No Known Activations