© 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. 5193
    Prev
    Next
    INDEX
    Explanations

    curtains or veil

    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
    ubo
    -0.09
     wheel
    -0.09
    iat
    -0.09
     crunch
    -0.09
    Subtitle
    -0.09
    assen
    -0.09
     cog
    -0.09
    enz
    -0.08
     rabbit
    -0.08
    annt
    -0.08
    POSITIVE LOGITS
     curtains
    0.17
     curtain
    0.17
    /window
    0.14
     Curtain
    0.11
    -covered
    0.11
     parted
    0.10
     fabrics
    0.10
    /part
    0.10
     veil
    0.10
     Curt
    0.10
    Activations Density 0.031%

    No Known Activations