© 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. 3443
    Prev
    Next
    INDEX
    Explanations

    code delimiters and separators

    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
    -aff
    -0.09
    asis
    -0.09
    Ķ
    -0.09
     lap
    -0.09
     goods
    -0.09
     Pru
    -0.09
    aksi
    -0.09
    amer
    -0.09
    affe
    -0.08
    otine
    -0.08
    POSITIVE LOGITS
    cobra
    0.09
     Jazz
    0.09
    ruc
    0.09
    Mismatch
    0.09
     lob
    0.08
    Sharper
    0.08
     Rubio
    0.08
     Peggy
    0.08
    usher
    0.08
     lawy
    0.08
    Activations Density 0.161%

    No Known Activations