© 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. 4071
    Prev
    Next
    INDEX
    Explanations

    code delimiters followed by code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    osing
    -0.09
    ilib
    -0.09
     shelves
    -0.09
     trough
    -0.09
     apro
    -0.08
     arguably
    -0.08
    -turned
    -0.08
    abis
    -0.08
     st
    -0.08
    ken
    -0.08
    POSITIVE LOGITS
    estate
    0.10
    gran
    0.10
     zoom
    0.10
     naam
    0.09
    ,\↵
    0.09
     lux
    0.09
     simpl
    0.09
    doll
    0.09
     singly
    0.09
     rusty
    0.09
    Activations Density 0.012%

    No Known Activations