© 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. 16406
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     jitter
    -0.09
     barric
    -0.08
     parity
    -0.08
     rural
    -0.07
     standoff
    -0.07
     accordion
    -0.07
     Rural
    -0.07
     Straw
    -0.07
     bump
    -0.07
     nos
    -0.07
    POSITIVE LOGITS
     totalitarian
    0.16
     ensl
    0.14
     dyst
    0.13
     Mastery
    0.13
     sinister
    0.13
     slave
    0.13
     BDSM
    0.13
     tyr
    0.13
     tot
    0.12
    alchemy
    0.12
    Activations Density 0.000%

    No Known Activations