© 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. 115982
    Prev
    Next
    INDEX
    Explanations

    wasting pity scorn disdain

    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
     ace
    -0.11
     subs
    -0.11
     illegally
    -0.10
     surrendered
    -0.09
     layout
    -0.09
     sac
    -0.09
     Privacy
    -0.09
     unauthorized
    -0.09
     obey
    -0.09
     reconc
    -0.09
    POSITIVE LOGITS
     pity
    0.18
     wasting
    0.16
     disdain
    0.16
     contempt
    0.16
     ridicule
    0.16
     waste
    0.16
     disgust
    0.16
     scorn
    0.15
     wastes
    0.15
     disgusted
    0.14
    Activations Density 0.054%

    No Known Activations