© 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. 33241
    Prev
    Next
    INDEX
    Explanations

    previous model or version

    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
     Incorporated
    -0.12
     habitual
    -0.11
     Veranst
    -0.11
     cleanliness
    -0.11
    AGMA
    -0.11
    å±Ģ
    -0.11
    Sites
    -0.11
     LOCAL
    -0.11
     unpaid
    -0.11
     Ej
    -0.11
    POSITIVE LOGITS
     discontinued
    0.20
     marketed
    0.17
     flagship
    0.17
     priced
    0.15
     offerings
    0.15
     designs
    0.15
    款
    0.15
     specs
    0.14
     manufactured
    0.14
     designed
    0.14
    Activations Density 0.644%

    No Known Activations