© 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. 92358
    Prev
    Next
    INDEX
    Explanations

    wright or right

    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
     IRA
    -0.08
    igit
    -0.08
     reasoning
    -0.08
    aho
    -0.07
    richt
    -0.07
    itar
    -0.07
    ollo
    -0.07
    umption
    -0.07
    ock
    -0.07
    asio
    -0.07
    POSITIVE LOGITS
    enment
    0.24
    eous
    0.22
    mare
    0.21
    ened
    0.21
    tps
    0.20
    edly
    0.20
    ening
    0.19
    een
    0.18
    ech
    0.15
    fully
    0.15
    Activations Density 0.011%

    No Known Activations