© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 89039
    Prev
    Next
    INDEX
    Explanations

    babble, babel, abal

    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
    atoi
    -0.09
    employer
    -0.09
    isty
    -0.08
     ath
    -0.08
    REP
    -0.08
    chner
    -0.08
     Alo
    -0.08
    lag
    -0.08
     Colbert
    -0.08
     lag
    -0.08
    POSITIVE LOGITS
     nonsense
    0.16
     bab
    0.12
    -mouth
    0.11
    -about
    0.11
     insane
    0.11
    ream
    0.11
     gib
    0.10
     Morse
    0.10
     Pipes
    0.10
    bling
    0.10
    Activations Density 0.019%

    No Known Activations