© 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. 33673
    Prev
    Next
    INDEX
    Explanations

    marino, is, wood, les, uni

    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
     bib
    -0.10
     spr
    -0.09
     EI
    -0.08
    SPI
    -0.08
    indi
    -0.08
     CIM
    -0.08
     pulp
    -0.08
     IM
    -0.07
     FI
    -0.07
    igm
    -0.07
    POSITIVE LOGITS
    ritz
    0.10
     unsett
    0.10
     Pornhub
    0.09
     Middleton
    0.09
    awl
    0.09
    Slots
    0.09
    _acl
    0.09
    saving
    0.09
     adm
    0.09
    avel
    0.09
    Activations Density 0.249%

    No Known Activations