© 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. 25145
    Prev
    Next
    INDEX
    Explanations

    transition metal, partition

    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
    ishly
    -0.10
    iness
    -0.10
    ground
    -0.10
    IES
    -0.10
    book
    -0.09
    alog
    -0.09
    let
    -0.09
    ish
    -0.09
    holds
    -0.09
     unp
    -0.08
    POSITIVE LOGITS
    ting
    0.15
     sleeper
    0.10
    jom
    0.10
    /loading
    0.10
    ween
    0.10
    akra
    0.10
    nya
    0.10
    343
    0.09
    ted
    0.09
     searchTerm
    0.09
    Activations Density 0.066%

    No Known Activations