© 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. 89958
    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
     Leaving
    -0.10
     allot
    -0.09
     yours
    -0.09
     Ha
    -0.09
     orphan
    -0.09
     owners
    -0.09
     Duncan
    -0.09
    rights
    -0.09
     paired
    -0.09
     Erg
    -0.09
    POSITIVE LOGITS
    adaptive
    0.10
     penetr
    0.10
     circum
    0.09
     Kes
    0.09
    adol
    0.08
    /ca
    0.08
    ileen
    0.08
     dame
    0.08
    aks
    0.08
     Opport
    0.08
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.