© 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. 112159
    Prev
    Next
    INDEX
    Explanations

    said, "this"

    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
     roaming
    -0.13
     roam
    -0.12
     recru
    -0.11
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.10
     organised
    -0.10
     Guides
    -0.10
    .initState
    -0.10
     Positions
    -0.10
     Alerts
    -0.10
     wyst
    -0.10
    POSITIVE LOGITS
     inspect
    0.18
     inspection
    0.16
     inspected
    0.15
     ownership
    0.14
     confisc
    0.14
     its
    0.14
     craftsmanship
    0.13
     handed
    0.13
     Ownership
    0.13
     contents
    0.13
    Activations Density 0.209%

    No Known Activations