© 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. 88360
    Prev
    Next
    INDEX
    Explanations

    timestamps and offsets

    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
     Ole
    -0.09
    gem
    -0.09
     Raphael
    -0.09
    -hot
    -0.09
     thirsty
    -0.08
     suddenly
    -0.08
     sank
    -0.08
    ister
    -0.08
    anova
    -0.08
     Mik
    -0.08
    POSITIVE LOGITS
     cac
    0.10
     Jack
    0.09
     JACK
    0.09
     enc
    0.09
     wg
    0.09
    wcs
    0.09
     Lie
    0.09
    ogs
    0.09
     MOT
    0.09
    /DD
    0.09
    Activations Density 0.001%

    No Known Activations