© 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. 48289
    Prev
    Next
    INDEX
    Explanations

    chains and locks

    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
    faction
    -0.11
     collapsed
    -0.11
    IDD
    -0.10
     hostages
    -0.10
     trapped
    -0.10
     bundles
    -0.10
     jelly
    -0.09
     Bund
    -0.09
     bund
    -0.09
     extraction
    -0.09
    POSITIVE LOGITS
     chain
    0.15
     rust
    0.13
    chain
    0.13
     rusty
    0.12
     Chain
    0.12
     brass
    0.12
     chains
    0.12
    -chain
    0.12
     forged
    0.12
     clang
    0.12
    Activations Density 0.058%

    No Known Activations