© 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. 113706
    Prev
    Next
    INDEX
    Explanations

    bath and shower

    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
     baths
    -0.18
     bathtub
    -0.17
     bath
    -0.17
     bathing
    -0.15
     Baths
    -0.15
     Bath
    -0.14
     bats
    -0.13
     bathroom
    -0.12
     bathrooms
    -0.12
     Bathroom
    -0.12
    POSITIVE LOGITS
    odel
    0.13
     McGregor
    0.11
    eldo
    0.10
    isque
    0.10
    agn
    0.10
     fizz
    0.10
    indy
    0.10
     handjob
    0.10
    folio
    0.10
     rose
    0.10
    Activations Density 0.077%

    No Known Activations