© 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. 50421
    Prev
    Next
    INDEX
    Explanations

    wet, cold, or contaminated

    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
    /pol
    -0.10
    winter
    -0.09
     Winter
    -0.09
    Winter
    -0.09
     Becker
    -0.08
     winter
    -0.08
    balls
    -0.08
    be
    -0.08
    -dom
    -0.08
    ButtonClick
    -0.08
    POSITIVE LOGITS
     absorb
    0.17
     soaked
    0.16
     wet
    0.16
     absorbing
    0.16
     soak
    0.15
     absor
    0.15
     damp
    0.15
     soaking
    0.15
     tainted
    0.14
     contaminated
    0.14
    Activations Density 0.031%

    No Known Activations