© 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. 18649
    Prev
    Next
    INDEX
    Explanations

    statistically, statute, statline, statsquare

    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
     Werner
    -0.09
    ér
    -0.08
    ebin
    -0.08
     Giuliani
    -0.08
     Kant
    -0.07
    æ°
    -0.07
    akov
    -0.07
     Fatal
    -0.07
    owment
    -0.07
     compet
    -0.07
    POSITIVE LOGITS
    istical
    0.18
     quo
    0.17
    uary
    0.16
    utory
    0.16
    istically
    0.15
    istic
    0.14
    emachine
    0.14
    ements
    0.13
    quo
    0.13
    hread
    0.13
    Activations Density 0.034%

    No Known Activations