© 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. 28753
    Prev
    Next
    INDEX
    Explanations

    toilets and related facilities

    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
    uten
    -0.10
    aq
    -0.09
    اء
    -0.09
    LEC
    -0.08
     Actual
    -0.08
    ej
    -0.08
    igner
    -0.08
     Internal
    -0.08
     fut
    -0.08
     blindly
    -0.08
    POSITIVE LOGITS
     repair
    0.14
     cleaner
    0.13
    repair
    0.12
     Patrol
    0.12
     Repair
    0.12
     cleaners
    0.12
    /rest
    0.12
    /workspace
    0.12
     bowl
    0.11
     repaired
    0.11
    Activations Density 0.009%

    No Known Activations