© 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. 91236
    Prev
    Next
    INDEX
    Explanations

    consequence indicating reason

    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
     Ain
    -0.10
     wisely
    -0.09
     thankfully
    -0.09
    outu
    -0.08
     conveniently
    -0.08
     ironically
    -0.08
    ilen
    -0.08
     medium
    -0.08
     Fior
    -0.07
     Gore
    -0.07
    POSITIVE LOGITS
     allows
    0.17
     Means
    0.17
     Allows
    0.16
    means
    0.15
    allows
    0.15
     means
    0.15
    Allows
    0.15
     then
    0.14
     allowing
    0.14
     implies
    0.14
    Activations Density 0.238%

    No Known Activations