© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 18062
    Prev
    Next
    INDEX
    Explanations

    names and brand names

    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
     ...↵
    -0.09
     ...↵↵
    -0.09
    otron
    -0.08
     RU
    -0.07
     Schwe
    -0.07
    .Sin
    -0.06
     bilateral
    -0.06
    htaking
    -0.06
    LOSS
    -0.06
     Brother
    -0.06
    POSITIVE LOGITS
     ihm
    0.11
     Cleaner
    0.11
     Dresses
    0.11
    /misc
    0.10
     Ting
    0.10
     wym
    0.10
     morals
    0.10
    aceous
    0.10
     commerc
    0.10
     Orr
    0.10
    Activations Density 0.105%

    No Known Activations