© 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. 33590
    Prev
    Next
    INDEX
    Explanations

    some picture or item

    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
    zell
    -0.09
    uba
    -0.09
    elson
    -0.09
    prd
    -0.09
     chi
    -0.09
     McGregor
    -0.09
     hur
    -0.08
     prelim
    -0.08
     hans
    -0.08
    while
    -0.08
    POSITIVE LOGITS
     somewhere
    0.42
    Som
    0.21
     somew
    0.20
     Som
    0.19
     downstairs
    0.18
     upstairs
    0.18
    som
    0.17
     elsewhere
    0.15
     here
    0.15
     Sommer
    0.15
    Activations Density 0.092%

    No Known Activations