© 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. 87730
    Prev
    Next
    INDEX
    Explanations

    too much

    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
    erto
    -0.11
     forgiving
    -0.10
     imperfect
    -0.10
    rtc
    -0.09
     rtc
    -0.09
    Forgot
    -0.08
    iali
    -0.08
     slightly
    -0.08
     darkest
    -0.08
     dele
    -0.08
    POSITIVE LOGITS
     overly
    0.32
     excessively
    0.30
     unnecessarily
    0.27
     constantly
    0.25
     too
    0.25
     excessive
    0.24
    too
    0.21
     Too
    0.21
     TOO
    0.20
     Constant
    0.19
    Activations Density 0.075%

    No Known Activations