© 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. 25381
    Prev
    Next
    INDEX
    Explanations

    cave

    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
     downstairs
    -0.13
    eren
    -0.13
    omp
    -0.12
     upstairs
    -0.12
    jom
    -0.11
    warts
    -0.11
    lä
    -0.11
    nergy
    -0.11
    uple
    -0.11
     submodule
    -0.11
    POSITIVE LOGITS
     entrance
    0.11
    Entr
    0.10
     passages
    0.09
     Kelvin
    0.09
     mouth
    0.09
     Entrance
    0.09
     leading
    0.09
     entrances
    0.08
     system
    0.08
     formations
    0.08
    Activations Density 0.019%

    No Known Activations