© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 5972
    Prev
    Next
    INDEX
    Explanations

    licensed legal disclaimers

    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
    nez
    -0.11
    sez
    -0.11
     Teh
    -0.10
    ulen
    -0.10
    Made
    -0.09
    -too
    -0.09
    én
    -0.09
    /live
    -0.09
     Mechanics
    -0.09
    ness
    -0.09
    POSITIVE LOGITS
     Pall
    0.09
    illac
    0.08
    mill
    0.08
     own
    0.08
    kir
    0.07
    styl
    0.06
     Paradise
    0.06
    ashboard
    0.06
    [top
    0.06
     Testament
    0.06
    Activations Density 0.007%

    No Known Activations