© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 87841
    Prev
    Next
    INDEX
    Explanations

    founder of

    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
    Negative Logits
    opher
    -0.09
     buz
    -0.09
    362
    -0.09
     Presents
    -0.09
    nu
    -0.08
    von
    -0.08
    angers
    -0.08
    thern
    -0.08
     McCart
    -0.08
     rectangular
    -0.08
    POSITIVE LOGITS
     former
    0.19
     founder
    0.15
     member
    0.15
     initiator
    0.15
     holder
    0.14
     owner
    0.14
     winner
    0.14
     sometime
    0.14
     longtime
    0.13
     protector
    0.13
    Activations Density 0.274%

    No Known Activations