© 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. 46919
    Prev
    Next
    INDEX
    Explanations

    general topics and concepts

    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
    ove
    -0.10
    ãĢĤ(
    -0.10
     til
    -0.09
     hurl
    -0.08
    entries
    -0.08
    ello
    -0.08
     pes
    -0.08
     bud
    -0.08
     courtesy
    -0.08
     breathtaking
    -0.08
    POSITIVE LOGITS
    eker
    0.10
     therefore
    0.10
     Pom
    0.10
     Thorn
    0.10
     thereby
    0.09
     furthermore
    0.09
    ivi
    0.09
     thus
    0.09
     hereby
    0.09
    azen
    0.09
    Activations Density 1.395%

    No Known Activations