© 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. 7939
    Prev
    Next
    INDEX
    Explanations

    bundled with

    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
    ifest
    -0.10
    548
    -0.10
    EA
    -0.09
     ambit
    -0.09
     Essex
    -0.09
    rick
    -0.09
     disqualified
    -0.09
    mans
    -0.09
     toe
    -0.09
    vely
    -0.09
    POSITIVE LOGITS
     why
    0.13
    ÑĢов
    0.11
    why
    0.10
     unseen
    0.10
    fall
    0.09
     suitable
    0.09
     Ling
    0.09
     available
    0.08
     conducive
    0.08
    yun
    0.08
    Activations Density 0.128%

    No Known Activations