© 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. 8044
    Prev
    Next
    INDEX
    Explanations

    time remaining

    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
    /c
    -0.09
     chill
    -0.08
     Walton
    -0.08
     back
    -0.08
    )}</
    -0.08
    ken
    -0.08
     zurück
    -0.08
     Richie
    -0.08
     Last
    -0.08
     dis
    -0.07
    POSITIVE LOGITS
    -tm
    0.12
    rien
    0.11
    /generated
    0.11
    arda
    0.11
    agu
    0.10
    ensch
    0.10
    lov
    0.10
    stin
    0.10
    unas
    0.10
    FML
    0.09
    Activations Density 0.008%

    No Known Activations