© 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. 31886
    Prev
    Next
    INDEX
    Explanations

    sharing, letting us know, suggesting, or making

    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
     centrally
    -0.10
     Edmund
    -0.10
     sever
    -0.08
     automatically
    -0.08
     Regina
    -0.08
     rub
    -0.08
    leo
    -0.08
     places
    -0.08
     tatto
    -0.08
     <>
    -0.08
    POSITIVE LOGITS
    -spec
    0.11
    ildo
    0.10
     Cav
    0.10
    ambi
    0.10
     cathedral
    0.10
     Baldwin
    0.10
    ype
    0.10
     hypoth
    0.09
    imax
    0.09
    -orange
    0.09
    Activations Density 0.001%

    No Known Activations