© 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. 47146
    Prev
    Next
    INDEX
    Explanations

    stairs and steps

    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
    azzi
    -0.08
     reflux
    -0.08
    cow
    -0.08
     Pe
    -0.08
    wares
    -0.08
    ichten
    -0.08
     Shah
    -0.08
     Thu
    -0.08
     penc
    -0.08
     adul
    -0.07
    POSITIVE LOGITS
     stairs
    0.42
     steps
    0.38
    steps
    0.30
     Steps
    0.30
     staircase
    0.29
     stair
    0.28
    stairs
    0.27
    Steps
    0.26
     ramp
    0.24
     step
    0.24
    Activations Density 0.089%

    No Known Activations