© 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. 90366
    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
     grap
    -0.07
    alus
    -0.07
     fundament
    -0.06
     Conspiracy
    -0.06
    anch
    -0.06
     Ank
    -0.06
     inher
    -0.06
    ä¿¡
    -0.06
    Trader
    -0.06
    icap
    -0.06
    POSITIVE LOGITS
     ips
    0.12
    trl
    0.11
    pei
    0.11
     Branch
    0.11
    adas
    0.11
    Keith
    0.11
    Pt
    0.11
     contrario
    0.11
     sak
    0.11
     exp
    0.11
    Activations Density 0.000%

    No Known Activations