© 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. 29160
    Prev
    Next
    INDEX
    Explanations

    this [significant noun]

    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
    isan
    -0.11
    haps
    -0.10
     spiel
    -0.09
     stint
    -0.09
     subjected
    -0.09
    yr
    -0.09
     linger
    -0.09
     dood
    -0.09
     ordeal
    -0.09
    alach
    -0.09
    POSITIVE LOGITS
     hated
    0.15
     most
    0.13
     crucial
    0.13
     important
    0.12
     celebrated
    0.12
     defining
    0.12
     remarkable
    0.11
     simplest
    0.11
     curious
    0.11
     familiar
    0.11
    Activations Density 0.119%

    No Known Activations