© 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. 49875
    Prev
    Next
    INDEX
    Explanations

    the terms

    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
     Apartment
    -0.08
     topp
    -0.07
     showcase
    -0.07
    Che
    -0.07
     worsh
    -0.07
     Chester
    -0.07
     showcasing
    -0.07
     che
    -0.07
     showcases
    -0.07
    alue
    -0.07
    POSITIVE LOGITS
     perf
    0.12
     churn
    0.12
    acre
    0.11
    endo
    0.11
    /cal
    0.11
     steer
    0.11
    cab
    0.10
     Explosion
    0.10
     advertised
    0.10
     Hubb
    0.10
    Activations Density 0.001%

    No Known Activations