© 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. 28915
    Prev
    Next
    INDEX
    Explanations

    versatile

    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
    Statics
    -0.10
     Roads
    -0.10
    Payments
    -0.10
    Owners
    -0.10
     Foods
    -0.10
     pret
    -0.10
     Pregn
    -0.09
    sd
    -0.09
     Bedrooms
    -0.09
     Voters
    -0.09
    POSITIVE LOGITS
     Vers
    0.19
     versatile
    0.17
     diverse
    0.15
     Enhanced
    0.15
     varied
    0.14
     versatility
    0.14
    Vers
    0.14
     variety
    0.13
     -*
    0.13
     unparalleled
    0.13
    Activations Density 0.091%

    No Known Activations