© 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. 7539
    Prev
    Next
    INDEX
    Explanations

    for free, for sale, for fun

    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
     contracting
    -0.09
     lem
    -0.08
    rides
    -0.08
     contracted
    -0.08
     Floyd
    -0.08
     sooner
    -0.08
     Ter
    -0.08
     Unused
    -0.08
     coll
    -0.07
     writable
    -0.07
    POSITIVE LOGITS
     fans
    0.16
     viewing
    0.16
     download
    0.14
     Fans
    0.13
     Viewing
    0.13
     consumption
    0.13
    desktop
    0.12
     aficion
    0.12
    fans
    0.12
     tablet
    0.12
    Activations Density 0.041%

    No Known Activations