© 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. 25335
    Prev
    Next
    INDEX
    Explanations

    HD followed by settings or model numbers

    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
    iaux
    -0.10
     overst
    -0.10
    kal
    -0.10
    anan
    -0.10
     {}:
    -0.10
    IME
    -0.10
     Presented
    -0.10
     Emerald
    -0.09
    dge
    -0.09
    orang
    -0.09
    POSITIVE LOGITS
    ified
    0.10
    ocre
    0.08
     relief
    0.08
     resolution
    0.08
    hir
    0.08
     conseg
    0.08
    Highest
    0.08
     toen
    0.08
     Hodg
    0.08
     version
    0.08
    Activations Density 0.004%

    No Known Activations