© 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. 32480
    Prev
    Next
    INDEX
    Explanations

    numbers followed by dates or tags

    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
     sidel
    -0.10
     overrides
    -0.09
    Ranked
    -0.09
     toile
    -0.08
     Bair
    -0.08
     opposes
    -0.07
    ijke
    -0.07
     lamps
    -0.07
     vy
    -0.07
     capital
    -0.07
    POSITIVE LOGITS
     Tart
    0.11
    iger
    0.10
    IOC
    0.09
    à¹Į
    0.09
    uously
    0.09
     parent
    0.09
     talent
    0.09
    upplier
    0.09
     poster
    0.09
    /vendor
    0.09
    Activations Density 0.002%

    No Known Activations