© 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. 32327
    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
    -strokes
    -0.08
     nap
    -0.08
    touches
    -0.07
     Wes
    -0.07
     nud
    -0.07
     Interrupt
    -0.07
     Dunk
    -0.07
     Abed
    -0.07
    rep
    -0.07
    ennen
    -0.07
    POSITIVE LOGITS
     Graf
    0.11
    ici
    0.11
     identical
    0.11
    chron
    0.10
     chron
    0.10
    maal
    0.10
    ilik
    0.10
     immer
    0.10
     vic
    0.10
    Feat
    0.10
    Activations Density 0.000%

    No Known Activations