© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 114891
    Prev
    Next
    INDEX
    Explanations

    punishable, year, max, upto

    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
     neutr
    -0.10
    aksi
    -0.10
    esion
    -0.10
     ade
    -0.10
     alc
    -0.10
     Wilkinson
    -0.09
    /il
    -0.09
    uset
    -0.09
     Albert
    -0.09
     beep
    -0.09
    POSITIVE LOGITS
     maximum
    0.17
     upto
    0.16
     up
    0.15
     potentially
    0.13
     max
    0.12
     Maximum
    0.11
    maximum
    0.10
     imprisonment
    0.10
    Maximum
    0.10
    (max
    0.10
    Activations Density 0.149%

    No Known Activations