© 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. 117384
    Prev
    Next
    INDEX
    Explanations

    parts clean

    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
     opening
    -0.10
    bach
    -0.10
     Opening
    -0.09
    Opened
    -0.08
    ugg
    -0.08
     Needle
    -0.08
    CCI
    -0.08
    SF
    -0.08
    ugas
    -0.08
    eva
    -0.08
    POSITIVE LOGITS
    [length
    0.11
     plac
    0.11
     Burton
    0.11
     Middle
    0.10
     Dia
    0.10
    length
    0.10
     clean
    0.10
     Mara
    0.10
    LENGTH
    0.10
    -length
    0.10
    Activations Density 0.022%

    No Known Activations