© 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. 6856
    Prev
    Next
    INDEX
    Explanations

    parking, terrace, alarm, begging, rooftop, plate, drink, medicine

    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
     tote
    -0.09
     Hag
    -0.08
     Mes
    -0.08
    «
    -0.08
     staged
    -0.08
    ìłģ
    -0.08
     Deb
    -0.07
     staging
    -0.07
     subj
    -0.07
     Bethlehem
    -0.07
    POSITIVE LOGITS
     ocas
    0.11
     equipments
    0.11
     terrace
    0.11
     thematic
    0.11
     Wooden
    0.11
     paran
    0.11
    ernote
    0.11
    lef
    0.11
     pls
    0.11
     Knock
    0.11
    Activations Density 0.427%

    No Known Activations