© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 8103
    Prev
    Next
    INDEX
    Explanations

    tired of something

    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
    Negative Logits
     comfort
    -0.11
     enjoy
    -0.11
     enjoys
    -0.11
     enjoying
    -0.10
     comfortably
    -0.10
     unfortunate
    -0.10
     messy
    -0.09
     enjoyment
    -0.09
     comforts
    -0.09
     pang
    -0.09
    POSITIVE LOGITS
     constant
    0.22
     constantly
    0.21
     Constant
    0.19
    constant
    0.17
     CONSTANT
    0.17
    Constant
    0.17
     incess
    0.16
     pretending
    0.16
     continual
    0.15
     secrecy
    0.15
    Activations Density 0.071%

    No Known Activations