© 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. 29660
    Prev
    Next
    INDEX
    Explanations

    association with concepts

    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
     pseud
    -0.07
     Rosen
    -0.07
     Marsh
    -0.07
     theoretical
    -0.07
     subtle
    -0.06
    bens
    -0.06
     hypothetical
    -0.06
    isen
    -0.06
     myself
    -0.06
    ingen
    -0.06
    POSITIVE LOGITS
     conj
    0.34
     associate
    0.31
     synonymous
    0.27
     associ
    0.27
     association
    0.26
    conj
    0.25
     associates
    0.25
    associate
    0.25
     stere
    0.24
     assoc
    0.24
    Activations Density 0.357%

    No Known Activations