© 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. 27980
    Prev
    Next
    INDEX
    Explanations

    negative emotions and consequences

    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
     dubious
    -0.13
     coward
    -0.12
     wor
    -0.12
     caution
    -0.11
    adan
    -0.11
     cautious
    -0.11
    stakes
    -0.11
     ominous
    -0.10
     dreadful
    -0.10
     worrying
    -0.10
    POSITIVE LOGITS
     disappointment
    0.26
     disillusion
    0.25
     frustration
    0.23
     disappointed
    0.23
     resent
    0.22
     resentment
    0.21
     frustrated
    0.20
     disappoint
    0.19
     frustrations
    0.18
     dissatisfaction
    0.18
    Activations Density 0.177%

    No Known Activations