© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 48745
    Prev
    Next
    INDEX
    Explanations

    scrubbing vigorously or with harshness

    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
     dew
    -0.11
    pek
    -0.11
     casc
    -0.10
     Ritch
    -0.10
     Umb
    -0.10
     mata
    -0.10
     Dew
    -0.10
     tipping
    -0.10
     fluid
    -0.09
     Fluid
    -0.09
    POSITIVE LOGITS
     scrub
    0.22
     vigorously
    0.16
     Scr
    0.14
    scr
    0.13
     harder
    0.13
     merciless
    0.13
     harsh
    0.13
     scr
    0.12
     floors
    0.11
     rigor
    0.11
    Activations Density 0.006%

    No Known Activations