© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 47677
    Prev
    Next
    INDEX
    Explanations

    website/blog, cookies, development

    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
     astr
    -0.07
    ,Yes
    -0.06
    cstdint
    -0.06
     ([]
    -0.06
    abaj
    -0.06
    iving
    -0.06
     imp
    -0.06
     jer
    -0.06
     scav
    -0.06
    Appear
    -0.06
    POSITIVE LOGITS
    pite
    0.11
    ****************************************************************************
    0.10
    (exports
    0.10
    unlink
    0.10
     wr
    0.10
    =en
    0.10
    readOnly
    0.10
     Pied
    0.10
    Bindings
    0.10
     IPs
    0.10
    Activations Density 2.709%

    No Known Activations