© 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. 29108
    Prev
    Next
    INDEX
    Explanations

    absorbing liquids

    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
     Ribbon
    -0.12
     carved
    -0.10
     stap
    -0.10
     feder
    -0.10
     romance
    -0.09
    ho
    -0.09
     organ
    -0.09
    uchen
    -0.09
     PVC
    -0.09
     Brigham
    -0.08
    POSITIVE LOGITS
     wipe
    0.24
     wiping
    0.21
     wiped
    0.21
     wipes
    0.18
     absorbing
    0.14
     dab
    0.14
    wipe
    0.13
     mop
    0.13
     absorb
    0.13
     blot
    0.13
    Activations Density 0.082%

    No Known Activations