© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 27851
    Prev
    Next
    INDEX
    Explanations

    import java

    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
     Organisation
    -0.12
     Outcome
    -0.12
     orgas
    -0.11
    Outcome
    -0.10
    outcome
    -0.10
     outcomes
    -0.10
     outbreaks
    -0.10
     committing
    -0.10
     Organization
    -0.10
     commits
    -0.10
    POSITIVE LOGITS
    cko
    0.11
     fetus
    0.09
     vul
    0.08
     sno
    0.08
     Sno
    0.08
    ivas
    0.08
    FP
    0.08
     Voy
    0.08
    []{↵
    0.08
     afterwards
    0.08
    Activations Density 0.078%

    No Known Activations