© 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. 3544
    Prev
    Next
    INDEX
    Explanations

    list continuations and examples

    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
    /is
    -0.11
    deo
    -0.09
    /bl
    -0.09
    /non
    -0.08
    Anywhere
    -0.08
    abr
    -0.08
     Everywhere
    -0.08
    736
    -0.08
    isis
    -0.08
     Cha
    -0.08
    POSITIVE LOGITS
     stuff
    0.48
     etc
    0.44
     things
    0.38
    etc
    0.38
     Stuff
    0.36
    stuff
    0.34
     such
    0.32
    Stuff
    0.32
    _stuff
    0.27
     Things
    0.26
    Activations Density 0.185%

    No Known Activations