© 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. 116377
    Prev
    Next
    INDEX
    Explanations

    anxiety and nervousness

    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
     laz
    -0.13
     grief
    -0.11
     despair
    -0.11
     boredom
    -0.10
     grieving
    -0.10
     disappointment
    -0.10
     dolor
    -0.10
     sorrow
    -0.09
     bored
    -0.09
     negligence
    -0.09
    POSITIVE LOGITS
     jitter
    0.22
     anxious
    0.17
     tense
    0.16
     nervous
    0.16
     nerv
    0.16
     sweating
    0.16
     tension
    0.15
     paranoid
    0.15
     paranoia
    0.15
     shaky
    0.15
    Activations Density 0.041%

    No Known Activations