© 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. 7979
    Prev
    Next
    INDEX
    Explanations

    rhino or rhodesian

    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
     Donald
    -0.08
     Nev
    -0.08
    env
    -0.08
    Fed
    -0.08
     driving
    -0.08
    piring
    -0.08
    bian
    -0.08
     spun
    -0.08
    mj
    -0.08
    ache
    -0.08
    POSITIVE LOGITS
     grain
    0.11
     grains
    0.10
     Grain
    0.10
    asaki
    0.10
     defer
    0.10
    iry
    0.10
     scraps
    0.10
     coral
    0.09
     Manhattan
    0.09
    loh
    0.09
    Activations Density 0.005%

    No Known Activations