© 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. 46111
    Prev
    Next
    INDEX
    Explanations

    I hate doing or feeling

    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
     hilar
    -0.13
     unusual
    -0.12
     duly
    -0.11
     unthinkable
    -0.10
     unlikely
    -0.10
     atleast
    -0.10
     batt
    -0.10
     disastrous
    -0.10
     awhile
    -0.09
     interesting
    -0.09
    POSITIVE LOGITS
     anymore
    0.15
     unnecessarily
    0.13
     forced
    0.11
     wasting
    0.11
     compromises
    0.11
     unnecessary
    0.11
     Forced
    0.11
     Necessary
    0.11
     overly
    0.11
     EVER
    0.11
    Activations Density 0.056%

    No Known Activations