© 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. 27444
    Prev
    Next
    INDEX
    Explanations

    best choice

    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
     divers
    -0.10
     potentially
    -0.10
     neat
    -0.09
    orrow
    -0.09
     beautiful
    -0.09
     Bert
    -0.09
     multim
    -0.09
     juicy
    -0.09
     dense
    -0.09
     cute
    -0.09
    POSITIVE LOGITS
     preferred
    0.24
     unmatched
    0.24
     unparalleled
    0.22
     superiority
    0.21
    preferred
    0.21
     superior
    0.21
     trusted
    0.21
     Preferred
    0.21
     choice
    0.20
     premier
    0.20
    Activations Density 0.110%

    No Known Activations