© 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. 25770
    Prev
    Next
    INDEX
    Explanations

    column or columnar structures

    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
    yy
    -0.10
    yyy
    -0.09
    tings
    -0.09
     Toolkit
    -0.08
     Diy
    -0.08
    yyyy
    -0.08
    ito
    -0.08
    çīĩ
    -0.08
    amped
    -0.08
     tire
    -0.08
    POSITIVE LOGITS
    /column
    0.14
    ar
    0.14
    aris
    0.13
    (Column
    0.13
     column
    0.12
     getColumn
    0.12
    -column
    0.12
    (column
    0.12
     columns
    0.11
     pillar
    0.11
    Activations Density 0.074%

    No Known Activations