© 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. 112375
    Prev
    Next
    INDEX
    Explanations

    negative surprise and worry

    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
     appealing
    -0.11
     Spr
    -0.11
     worthy
    -0.11
     interesting
    -0.11
     deserving
    -0.11
     appeals
    -0.11
    @student
    -0.11
     deserves
    -0.10
     sounded
    -0.10
    oron
    -0.10
    POSITIVE LOGITS
     unn
    0.16
     unsettling
    0.13
     ominous
    0.12
     chilling
    0.12
     panic
    0.11
     worry
    0.11
     chilled
    0.11
     worrying
    0.11
    unset
    0.11
     unsett
    0.10
    Activations Density 0.020%

    No Known Activations