© 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. 50726
    Prev
    Next
    INDEX
    Explanations

    Department of

    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
    -0.12
    ings
    -0.10
    heet
    -0.10
    yan
    -0.10
    pell
    -0.09
    etime
    -0.09
    wort
    -0.09
    uchen
    -0.09
    pag
    -0.09
    Sheet
    -0.09
    POSITIVE LOGITS
    al
    0.31
    artment
    0.20
    alist
    0.14
    ial
    0.14
    /div
    0.13
    ally
    0.13
    alc
    0.12
    alles
    0.11
    -wide
    0.11
    arian
    0.11
    Activations Density 0.062%

    No Known Activations