© 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. 29050
    Prev
    Next
    INDEX
    Explanations

    washing and cleaning

    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
    jections
    -0.10
    sci
    -0.09
    Scient
    -0.09
    scalar
    -0.09
    rah
    -0.08
    toa
    -0.08
    gle
    -0.08
     resorts
    -0.08
     Pend
    -0.08
    NESS
    -0.08
    POSITIVE LOGITS
     Washing
    0.15
     dishes
    0.15
     laundry
    0.15
     Wash
    0.14
     washing
    0.14
    cloth
    0.14
     clothes
    0.14
     wash
    0.12
     washed
    0.12
    washing
    0.12
    Activations Density 0.043%

    No Known Activations