© 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. 91118
    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
     Bravo
    -0.12
    metics
    -0.11
    oman
    -0.11
    /runtime
    -0.10
    acked
    -0.10
     Lilly
    -0.10
    ments
    -0.10
    clared
    -0.10
    ено
    -0.10
     Jas
    -0.10
    POSITIVE LOGITS
    hive
    0.09
     mach
    0.08
    FLT
    0.08
     Floor
    0.08
     pall
    0.08
     marin
    0.08
    FREE
    0.08
     Benjamin
    0.07
     Gratis
    0.07
     malaysia
    0.07
    Activations Density 0.000%

    No Known Activations