© 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. 29605
    Prev
    Next
    INDEX
    Explanations

    existence and availability

    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
    GEST
    -0.10
     Await
    -0.10
    /int
    -0.10
     nobody
    -0.10
    ague
    -0.09
     doorstep
    -0.09
    centre
    -0.09
    paste
    -0.09
    aldo
    -0.09
     duly
    -0.09
    POSITIVE LOGITS
     present
    0.23
     involved
    0.17
    present
    0.15
     Present
    0.15
     available
    0.14
     exist
    0.13
     vorhand
    0.12
     prés
    0.11
     encountered
    0.11
    Present
    0.11
    Activations Density 0.178%

    No Known Activations