© 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. 114381
    Prev
    Next
    INDEX
    Explanations

    piercing, perforation

    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
    entin
    -0.09
    aque
    -0.09
     Cot
    -0.09
    otto
    -0.09
    ician
    -0.09
    tim
    -0.09
    tick
    -0.08
    из
    -0.08
    auge
    -0.08
    ober
    -0.08
    POSITIVE LOGITS
    ved
    0.11
     diagon
    0.10
    wort
    0.10
    ured
    0.09
    cing
    0.09
    morgan
    0.09
    grab
    0.09
     dang
    0.09
    mentation
    0.09
    ioned
    0.09
    Activations Density 0.023%

    No Known Activations