© 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. 24991
    Prev
    Next
    INDEX
    Explanations

    While followed by subject or adverbial phrase

    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
     Jenner
    -0.09
     nightmare
    -0.08
    ector
    -0.08
    uintptr
    -0.08
    blk
    -0.08
     bedtime
    -0.08
     Fritz
    -0.08
    tc
    -0.08
     juste
    -0.08
     lam
    -0.08
    POSITIVE LOGITS
     technically
    0.18
     initially
    0.16
     normally
    0.16
     ordinarily
    0.15
     originally
    0.14
     admittedly
    0.14
     Normally
    0.13
     Initially
    0.13
     certainly
    0.13
     waiting
    0.13
    Activations Density 0.030%

    No Known Activations