© 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. 117210
    Prev
    Next
    INDEX
    Explanations

    specific units of time or places

    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
    cha
    -0.10
     kor
    -0.09
     Kor
    -0.08
     principal
    -0.08
    aven
    -0.08
     Briggs
    -0.08
     Weber
    -0.07
     Zub
    -0.07
     flex
    -0.07
     sensible
    -0.07
    POSITIVE LOGITS
    icks
    0.13
    nr
    0.11
    elves
    0.11
    otron
    0.11
    moth
    0.11
     Typ
    0.11
    SHIFT
    0.11
    577
    0.10
    phia
    0.10
    OTA
    0.10
    Activations Density 0.647%

    No Known Activations