© 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. 31810
    Prev
    Next
    INDEX
    Explanations

    examine or inspect

    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
    rud
    -0.14
     bulld
    -0.12
     mop
    -0.11
     climb
    -0.11
    /arch
    -0.10
    dee
    -0.10
     Bulld
    -0.10
    icl
    -0.10
     epid
    -0.10
     climbing
    -0.10
    POSITIVE LOGITS
     examined
    0.18
     examining
    0.18
     inspect
    0.18
     examine
    0.18
     examination
    0.18
     inspected
    0.17
     Holding
    0.16
     Exam
    0.15
     examines
    0.15
    exam
    0.15
    Activations Density 0.107%

    No Known Activations