© 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. 33379
    Prev
    Next
    INDEX
    Explanations

    especially, particularly

    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
    }.
    -0.07
     presumption
    -0.06
     wen
    -0.06
    oder
    -0.06
     Tail
    -0.05
    istar
    -0.05
     irony
    -0.05
     dut
    -0.05
     sabot
    -0.05
     cra
    -0.05
    POSITIVE LOGITS
     ones
    0.40
     those
    0.27
    ones
    0.25
     Ones
    0.24
     Those
    0.23
    those
    0.23
    Those
    0.21
     ceux
    0.20
     ours
    0.19
     yours
    0.17
    Activations Density 0.367%

    No Known Activations