© 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. 33737
    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
    ajar
    -0.08
     pond
    -0.07
     Kee
    -0.07
    amel
    -0.07
     zie
    -0.07
    aben
    -0.06
     Midwest
    -0.06
     rinse
    -0.06
     Ses
    -0.06
     lem
    -0.06
    POSITIVE LOGITS
     transc
    0.15
     crave
    0.13
     craving
    0.13
    strup
    0.13
     mutually
    0.12
     intimacy
    0.12
     Liebe
    0.12
     plat
    0.12
    pla
    0.12
     taboo
    0.12
    Activations Density 0.000%

    No Known Activations