© 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. 32681
    Prev
    Next
    INDEX
    Explanations

    wild and preceding common suffixes

    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
    ault
    -0.10
    /watch
    -0.09
    476
    -0.09
     Eck
    -0.09
     aria
    -0.09
    ugen
    -0.08
    istical
    -0.08
    Ãłng
    -0.08
    206
    -0.08
    ills
    -0.08
    POSITIVE LOGITS
    erness
    0.19
    er
    0.16
    (er
    0.16
    erne
    0.15
    s
    0.15
    ernes
    0.14
    ness
    0.14
    ernet
    0.13
    erk
    0.12
    erland
    0.12
    Activations Density 0.016%

    No Known Activations