© 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. 29588
    Prev
    Next
    INDEX
    Explanations

    ratio of quantities

    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
    fulness
    -0.09
    screen
    -0.09
    bur
    -0.09
    ste
    -0.09
     Pope
    -0.08
    lee
    -0.08
    burst
    -0.08
    lear
    -0.08
    lessness
    -0.08
     thro
    -0.08
    POSITIVE LOGITS
    ä¾ĭ
    0.12
     maxim
    0.10
     Urg
    0.10
    PERT
    0.09
     CSL
    0.09
    iero
    0.09
    нÑĭ
    0.09
    ries
    0.09
     erg
    0.09
    AX
    0.09
    Activations Density 0.038%

    No Known Activations