© 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. 29500
    Prev
    Next
    INDEX
    Explanations

    this time

    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
     nowadays
    -0.20
     currently
    -0.16
     presently
    -0.16
     sometimes
    -0.14
     anymore
    -0.14
     therein
    -0.13
     atm
    -0.13
     today
    -0.13
    sometimes
    -0.13
    currently
    -0.13
    POSITIVE LOGITS
     explicitly
    0.11
     directly
    0.11
     consciously
    0.10
     outright
    0.09
     accompanied
    0.09
     upfront
    0.09
     explicit
    0.09
     conscious
    0.08
     genuinely
    0.08
     beforehand
    0.08
    Activations Density 0.058%

    No Known Activations