© 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. 49781
    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
     begging
    -0.10
    occo
    -0.09
    expo
    -0.08
    hest
    -0.08
    Latch
    -0.08
    atori
    -0.08
    bast
    -0.08
     granted
    -0.08
    PASS
    -0.08
    mouth
    -0.08
    POSITIVE LOGITS
     deg
    0.12
     Deg
    0.11
     Shea
    0.10
     Cher
    0.10
     bend
    0.10
    ein
    0.09
     perse
    0.09
    Deg
    0.09
     pers
    0.09
     haci
    0.09
    Activations Density 0.000%

    No Known Activations