© 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. 18462
    Prev
    Next
    INDEX
    Explanations

    in [topic]

    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
     Nail
    -0.09
     Crawford
    -0.08
    uu
    -0.08
    BN
    -0.08
     analyzer
    -0.08
     citizenship
    -0.08
    etz
    -0.08
     Sponsored
    -0.08
     Kerr
    -0.08
     PID
    -0.08
    POSITIVE LOGITS
     reve
    0.12
     fingertips
    0.10
     sidelines
    0.10
     McGu
    0.10
     meanwhile
    0.10
     outset
    0.10
     eve
    0.10
     aspects
    0.10
     weekdays
    0.10
    /of
    0.10
    Activations Density 0.439%

    No Known Activations