© 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. 17259
    Prev
    Next
    INDEX
    Explanations

    shared interests and opinions

    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
    loo
    -0.09
     accelerator
    -0.09
    jak
    -0.09
     integ
    -0.09
     humiliating
    -0.08
     inaccur
    -0.08
     plasma
    -0.08
    Features
    -0.08
     averaging
    -0.08
     dignity
    -0.08
    POSITIVE LOGITS
     similarly
    0.36
     shared
    0.29
     similar
    0.29
     agrees
    0.29
     agree
    0.27
    same
    0.26
     same
    0.25
     likewise
    0.25
     Shared
    0.25
    similar
    0.24
    Activations Density 0.201%

    No Known Activations