© 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. 89608
    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
     voluntarily
    -0.11
    plat
    -0.11
     Extr
    -0.11
     Rupert
    -0.10
     èĩ
    -0.10
    ideos
    -0.10
     Borough
    -0.10
     Mayor
    -0.10
    jak
    -0.10
     plat
    -0.10
    POSITIVE LOGITS
     compass
    0.09
    ettel
    0.09
     sweaty
    0.08
     fel
    0.08
     clap
    0.08
    tan
    0.07
    opa
    0.07
    misc
    0.07
     antid
    0.07
     slim
    0.07
    Activations Density 0.000%

    No Known Activations