© 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. 32522
    Prev
    Next
    INDEX
    Explanations

    special [word]

    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
     overdue
    -0.09
     apparent
    -0.09
    sel
    -0.08
    umar
    -0.08
     barely
    -0.08
    bai
    -0.08
    iken
    -0.08
     inevitable
    -0.08
     unavoidable
    -0.07
    isle
    -0.07
    POSITIVE LOGITS
     special
    0.21
    -special
    0.17
     SPECIAL
    0.17
     kind
    0.17
    special
    0.16
    Special
    0.16
     Special
    0.15
     KIND
    0.15
    çī¹
    0.14
     blend
    0.13
    Activations Density 0.057%

    No Known Activations