© 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. 34208
    Prev
    Next
    INDEX
    Explanations

    ball

    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
     Shields
    -0.11
     Garrison
    -0.10
     Lev
    -0.10
     shields
    -0.10
     rings
    -0.10
     binder
    -0.10
     Mobil
    -0.10
     insertion
    -0.09
     Binder
    -0.09
     Merc
    -0.09
    POSITIVE LOGITS
     ball
    0.20
    -ball
    0.15
    ball
    0.15
     Ball
    0.14
    Ball
    0.14
     balls
    0.14
     BALL
    0.13
     Balls
    0.12
    _ball
    0.11
     sno
    0.11
    Activations Density 0.007%

    No Known Activations