© 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. 46842
    Prev
    Next
    INDEX
    Explanations

    percentages

    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
    ego
    -0.09
    /Data
    -0.08
    .`
    -0.08
    faker
    -0.08
    _)
    -0.08
    *)
    -0.08
    /@
    -0.08
     Captain
    -0.08
    iken
    -0.07
    iller
    -0.07
    POSITIVE LOGITS
    %
    0.28
     percent
    0.27
    %,
    0.25
    %.
    0.22
    %.↵↵
    0.21
     %
    0.21
    %!
    0.19
    percent
    0.19
    %↵
    0.18
    -percent
    0.18
    Activations Density 0.339%

    No Known Activations