© 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. 8330
    Prev
    Next
    INDEX
    Explanations

    parked outside

    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
     Uhr
    -0.10
    ãĤ£
    -0.10
     Rossi
    -0.09
    ulary
    -0.09
     Mine
    -0.09
     proto
    -0.09
    Bu
    -0.09
     Parsons
    -0.09
     manual
    -0.09
    ););↵
    -0.09
    POSITIVE LOGITS
     outside
    0.19
     Outside
    0.17
     parked
    0.17
    Outside
    0.16
    outside
    0.16
     vehicle
    0.16
     car
    0.16
     cir
    0.15
     orbit
    0.15
    å¤ĸ
    0.14
    Activations Density 0.134%

    No Known Activations